© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7320
    Prev
    Next
    INDEX
    Explanations

    endor promote

    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
    ä¸įæ¸ħ
    -0.10
    ty
    -0.08
    åľ°å¸¦
    -0.08
    Sharp
    -0.08
    è´¯
    -0.07
    éĻªåIJĮ
    -0.07
    å¯Łçľĭ
    -0.07
    emen
    -0.07
     misc
    -0.07
    ä¸ĭæĿ¥
    -0.07
    POSITIVE LOGITS
    пÑĥÑģÑĤ
    0.10
    ENDOR
    0.10
    åŀ¸
    0.09
     ÐŃÑĤоÑĤ
    0.09
    羨
    0.09
    CNT
    0.09
    åĶı
    0.09
    åŦ
    0.09
    轩è¾ķ
    0.09
    æ¯
    0.09
    Activations Density 0.013%

    No Known Activations