© 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. 16950
    Prev
    Next
    INDEX
    Explanations

    save as file

    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
    onia
    -0.22
     MessageLookup
    -0.22
    Matchers
    -0.20
    .GET
    -0.20
    PropertyParams
    -0.20
     iNdEx
    -0.19
    .readLine
    -0.19
    inputEmail
    -0.19
    mPid
    -0.18
     Penalty
    -0.18
    POSITIVE LOGITS
    åĨĻåĩº
    0.26
    ToFile
    0.21
    ä¸įåIJĮç±»åŀĭ
    0.21
     outFile
    0.20
    ä¸Ģ个æĸ°çļĦ
    0.20
    åѦåijĺ
    0.20
    ä½ľåĵģ
    0.20
    æĽ´åIJį为
    0.20
    æĸ°çīĪ
    0.20
    _ISR
    0.19
    Activations Density 0.056%

    No Known Activations