© 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. 24046
    Prev
    Next
    INDEX
    Explanations

    coins, quarters

    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
    åĿ¨
    -0.10
    uv
    -0.10
    è¡¥é½IJ
    -0.09
    éľĵ
    -0.09
    票æį®
    -0.09
    ç»Į
    -0.09
    ÙĦاء
    -0.09
    å¼Ģä¸ļ
    -0.09
    ering
    -0.09
    ç³Ł
    -0.09
    POSITIVE LOGITS
     coin
    0.10
     coins
    0.09
     deb
    0.09
    èĢĺ
    0.09
    .coin
    0.08
    硬
    0.08
    ANTE
    0.08
     Coins
    0.08
    åĩ»
    0.08
    ä»·éĴ±
    0.08
    Activations Density 0.030%

    No Known Activations