© 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. 4792
    Prev
    Next
    INDEX
    Explanations

    news and facts

    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
    ique
    -0.11
    DEFINED
    -0.10
    uarios
    -0.09
    ä¸ĢèĦļ
    -0.09
    iers
    -0.09
    aires
    -0.09
    æŃ¥è¡Į
    -0.09
    çIJĨæĥ³çļĦ
    -0.09
     xlim
    -0.09
    	TokenName
    -0.09
    POSITIVE LOGITS
    è¯ģå®ŀ
    0.11
    羣å®ŀæĢ§
    0.11
    çļĦ羣å®ŀæĢ§
    0.10
    å®ŀäºĭæ±Ĥæĺ¯
    0.10
    羣缸
    0.09
    çĪĨæĸĻ
    0.09
    æł¸å®ŀ
    0.09
    伪éĢł
    0.08
    æī¿æĭħ责任
    0.08
    ç»ıæŁ¥
    0.08
    Activations Density 0.110%

    No Known Activations