© 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. 63618
    Prev
    Next
    INDEX
    Explanations

    hitting, biting, attacking

    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
    å¯ĨåĪĩ
    -0.09
    åľ¨åĮĹ京
    -0.09
    ç¼¢
    -0.09
    ration
    -0.09
    fid
    -0.09
    getAs
    -0.09
    ç¼Ł
    -0.08
     اÙĦجÙĨس
    -0.08
    FilterWhere
    -0.08
    aign
    -0.08
    POSITIVE LOGITS
    ç¾İ人
    0.09
    è¿ĻéĩĮçļĦ
    0.08
    èĦ¸
    0.08
     Wake
    0.08
    Surv
    0.08
    è®°
    0.08
    uchi
    0.08
    èµĸ以
    0.08
    enson
    0.08
    Ré
    0.08
    Activations Density 0.070%

    No Known Activations