© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 4786
    Prev
    Next
    INDEX
    Explanations

    inside a

    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
    份
    -0.08
    漪
    -0.08
    IfExists
    -0.08
    诺è´Ŀå°Ķ
    -0.08
    ä¸Ģæī¹
    -0.08
    èĮ¬
    -0.08
    è¾Ī
    -0.07
    FIXME
    -0.07
    轻微
    -0.07
    ç¥ł
    -0.07
    POSITIVE LOGITS
    å±ĭåŃIJ
    0.11
    /out
    0.09
    halb
    0.09
    æľī许å¤ļ
    0.09
    çĽĴåŃIJ
    0.09
    /on
    0.09
     Äijá»±ng
    0.09
    .relationship
    0.09
    æĿ¯åŃIJ
    0.09
     metab
    0.09
    Activations Density 0.091%

    No Known Activations