© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6020
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    amp
    -0.09
    çĴ§
    -0.08
    工信
    -0.08
    ç¢į
    -0.08
    _READONLY
    -0.08
    å½ĵåľ°
    -0.08
     ÐŁÐ¾Ñĩем
    -0.08
    urator
    -0.08
    zent
    -0.07
    mong
    -0.07
    POSITIVE LOGITS
    trak
    0.11
    äºĽ
    0.09
    ãģ¡
    0.09
    orld
    0.09
    å¿ĥ头
    0.08
    dex
    0.08
    大大
    0.08
    ucks
    0.08
    king
    0.08
    ieres
    0.08
    Activations Density 0.389%

    No Known Activations