© 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. 967
    Prev
    Next
    INDEX
    Explanations

    date and time stamps

    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
    aky
    -0.09
    åĻ«
    -0.09
    ç¥ŀè¯Ŀ
    -0.09
    itution
    -0.09
     ÐŁÐ¾Ñĩем
    -0.08
    æĬ¥ä¸ļ
    -0.08
    ToFile
    -0.08
    ä¸ĩçī©
    -0.08
    çī¯
    -0.08
    æī©å±ķ
    -0.08
    POSITIVE LOGITS
    å¸ĸåŃIJ
    0.09
    åĽŀå¤į
    0.09
     posts
    0.09
    à¸Ħม
    0.08
    _crop
    0.08
    /photo
    0.08
    /posts
    0.08
     GAM
    0.08
    pras
    0.08
    .facebook
    0.08
    Activations Density 0.027%

    No Known Activations