#include <algorithm>
#include <atcoder/all>
#include <bitset>
#include <cassert>
#include <cmath>
#include <ctime>
#include <functional>
#include <iomanip>
#include <iostream>
#include <map>
#include <queue>
#include <random>
#include <set>
#include <stack>
#include <string>
#include <tuple>
#include <unordered_map>
#include <unordered_set>
#include <utility>
#include <vector>
using namespace std;
using namespace atcoder;
typedef long long ll;
#define rep(i, n) for (int i = 0; i < (int)(n); i++)
#define repr(i, n) for (int i = (int)(n) - 1; i >= 0; i--)
#define repk(i, k, n) for (int i = k; i < (int)(n); i++)
#define all(v) v.begin(), v.end()
#define mod1 1000000007
#define mod2 998244353
#define mod3 100000007
#define vi vector<int>
#define vs vector<string>
#define vc vector<char>
#define vl vector<ll>
#define vb vector<bool>
#define vvi vector<vector<int>>
#define vvc vector<vector<char>>
#define vvl vector<vector<ll>>
#define vvb vector<vector<bool>>
#define vvvi vector<vector<vector<int>>>
#define vvvl vector<vector<vector<ll>>>
#define pii pair<int, int>
#define pil pair<int, ll>
#define pli pair<ll, int>
#define pll pair<ll, ll>
#define vpii vector<pair<int, int>>
#define vpll vector<pair<ll, ll>>
#define vvpii vector<vector<pair<int, int>>>
#define vvpll vector<vector<pair<ll, ll>>>

template <typename T>
void debug(T e) {
    cerr << e << endl;
}

template <typename T>
void debug(vector<T> &v) {
    rep(i, v.size()) { cerr << v[i] << " "; }
    cerr << endl;
}

template <typename T>
void debug(vector<vector<T>> &v) {
    rep(i, v.size()) {
        rep(j, v[i].size()) { cerr << v[i][j] << " "; }
        cerr << endl;
    }
}

template <typename T>
void debug(vector<pair<T, T>> &v) {
    rep(i, v.size()) { cerr << v[i].first << " " << v[i].second << endl; }
}

template <typename T>
void debug(set<T> &st) {
    for (auto itr = st.begin(); itr != st.end(); itr++) {
        cerr << *itr << " ";
    }
    cerr << endl;
}

template <typename T>
void debug(multiset<T> &ms) {
    for (auto itr = ms.begin(); itr != ms.end(); itr++) {
        cerr << *itr << " ";
    }
    cerr << endl;
}

template <typename T>
void debug(map<T, T> &mp) {
    for (auto itr = mp.begin(); itr != mp.end(); itr++) {
        cerr << itr->first << " " << itr->second << endl;
    }
}

void debug_out() { cerr << endl; }

template <typename Head, typename... Tail>
void debug_out(Head H, Tail... T) {
    cerr << H << " ";
    debug_out(T...);
}

using mint = modint998244353;

void debug_mint1(vector<mint> &vec) {
    for (int i = 0; i < vec.size(); i++) {
        cerr << vec[i].val() << " ";
    }
    cerr << endl;
}

void debug_mint2(vector<vector<mint>> &vec) {
    for (int i = 0; i < vec.size(); i++) {
        for (int j = 0; j < vec[i].size(); j++) {
            cerr << vec[i][j].val() << " ";
        }
        cerr << endl;
    }
}

int main(){
    ll T;
    cin >> T;
    while (T--){
        ll N, M;
        cin >> N >> M;
        vector<string> K(M);
        for (ll i = 0; i < M; i++){
            cin >> K[i];
        }
        if (N == 0){
            for (ll i = 0; i < M; i++){
                cout << 1 << endl;
            }
            continue;
        }
        // N^i の周期を求める
        vector<vector<ll>> last_val(998, vector<ll>(998, -1));
        vector<ll> min_point(1, 1);
        last_val[1][1] = 0;
        ll now_cnt = 0;
        ll now = 1;
        ll now_sum = 1;
        ll loop, rem;
        while (true){
            now_cnt++;
            ll nx_now = (now * N) % 998;
            ll nx_sum = (now_sum + nx_now) % 998;
            if (last_val[nx_now][nx_sum] != -1){
                loop = now_cnt - last_val[nx_now][nx_sum];
                rem = last_val[nx_now][nx_sum];
                break;
            }
            now = nx_now;
            now_sum = nx_sum;
            last_val[now][now_sum] = now_cnt;
            min_point.push_back(now_sum);
        }

        for (ll i = 0; i < M; i++){
            if (K[i].size() <= 7){
                ll len = stoll(K[i]);
                if (len < min_point.size()){
                    cout << min_point[len] << endl;
                }
                else{
                    len -= rem;
                    cout << min_point[len % loop + rem] << endl;
                }
            }
            else{
                // あまりを求める
                ll lrem = 0;
                for (ll j = 0; j < K[i].size(); j++){
                    lrem *= 10;
                    lrem += (ll)(K[i][j] - '0');
                    lrem %= loop;
                }
                lrem = (lrem + 998 * loop - rem) % loop;
                cout << min_point[lrem + rem] << endl;
            }
        }
    }
}