© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 13571
    Prev
    Next
    INDEX
    Explanations

    cheating and affairs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    妥
    -0.21
    é¢Ĩåıĸ
    -0.20
    éģķãģĦ
    -0.20
    转åĮĸ
    -0.19
     Robots
    -0.19
    ç²Ĺ
    -0.19
    æŃ¹
    -0.19
    .openg
    -0.18
    æĤŃ
    -0.17
    æ¶Īè´¹åĵģ
    -0.17
    POSITIVE LOGITS
     PIN
    0.19
     thr
    0.18
    æĸ¡
    0.18
    _workspace
    0.17
    èĦ²
    0.17
    éķ¿éĢĶ
    0.17
    çī
    0.17
    strained
    0.17
    çŃł
    0.17
    .spatial
    0.17
    Activations Density 0.007%

    No Known Activations