© 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. 18992
    Prev
    Next
    INDEX
    Explanations

    several [adjective/quantifier]

    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
    æĢ¯
    -0.09
    lov
    -0.09
    è¢Ń
    -0.08
    apiro
    -0.08
    è¨Ģ论
    -0.08
    coll
    -0.08
    大åѦçĶŁ
    -0.08
    çł»
    -0.08
     READ
    -0.08
    à¸Ńà¸ģ
    -0.08
    POSITIVE LOGITS
    å®Įåħ¨ä¸įåIJĮ
    0.12
    æĿ¥åĽŀ
    0.11
    çĶļèĩ³æĺ¯
    0.10
    umph
    0.10
    ç¨Ģ
    0.09
    ç»ıå¼Ģ
    0.09
    ä¸įåIJĮçļĦ
    0.09
    ļĮ
    0.09
    åı¯çĶ¨
    0.09
    æµĭç»ĺ
    0.09
    Activations Density 0.082%

    No Known Activations