© 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. 21957
    Prev
    Next
    INDEX
    Explanations

    names followed by surnames

    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
     himself
    -0.10
    çļĦ妻åŃIJ
    -0.10
    åĸĻ
    -0.10
    оÑĩнÑĭй
    -0.10
    æĪijéĻ¢
    -0.09
     СеÑĢгей
    -0.09
    bas
    -0.09
     ÙĨÙģسÙĩ
    -0.08
    erval
    -0.08
    该æĿij
    -0.08
    POSITIVE LOGITS
    æĢİæł·
    0.10
    /he
    0.10
    é¾Ľ
    0.09
    嫱
    0.09
    å®īå¨ľ
    0.09
    çīĩåŃIJ
    0.09
    riad
    0.09
    æľī两ç§į
    0.09
    娲
    0.09
    hood
    0.09
    Activations Density 0.170%

    No Known Activations