© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 16944
    Prev
    Next
    INDEX
    Explanations

    induction

    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
    makt
    -0.19
    anka
    -0.19
    Ñĥж
    -0.18
    _HOLD
    -0.18
    validators
    -0.18
    ActionCode
    -0.17
    ç«Ń
    -0.17
    ä¸ĢåĽŀäºĭ
    -0.16
    getUrl
    -0.16
    getView
    -0.16
    POSITIVE LOGITS
     into
    0.28
    _into
    0.23
    into
    0.23
    Into
    0.23
    ees
    0.22
     vÃło
    0.21
    onto
    0.21
    italize
    0.21
    ively
    0.21
     onto
    0.20
    Activations Density 0.007%

    No Known Activations