© 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. 16068
    Prev
    Next
    INDEX
    Explanations

    col, percentage, source, IDE

    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
    drs
    -0.22
    ç«Ļéķ¿
    -0.20
     ÐŁÐ¾Ñĩем
    -0.18
    éĥİ
    -0.18
    _QMARK
    -0.17
    Accessible
    -0.17
    ?f
    -0.17
     ÑģоÑħÑĢ
    -0.17
    #${
    -0.17
     Erot
    -0.17
    POSITIVE LOGITS
    两大
    0.20
    ä¸ĵåijĺ
    0.20
    ÑģÑģ
    0.19
    _vue
    0.18
     Holds
    0.17
    "..
    0.17
    eld
    0.17
     Randall
    0.17
     Wh
    0.17
    elves
    0.17
    Activations Density 0.625%

    No Known Activations