© 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. 10440
    Prev
    Next
    INDEX
    Explanations

    yarn or texture description

    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
    æ¢ĵ
    -0.10
    èļĮ
    -0.09
    éĴ¢æĿ¿
    -0.09
    ä¸¤å¼ł
    -0.09
    æ²Ļ滩
    -0.09
    涧
    -0.09
    é©°
    -0.09
     unlawful
    -0.08
    -runtime
    -0.08
    æ³®
    -0.08
    POSITIVE LOGITS
    好似
    0.08
    忱
    0.08
    itecture
    0.08
     liner
    0.08
    isode
    0.08
    ä¿Ŀæļĸ
    0.08
    itre
    0.08
    éĥ½å·²ç»ı
    0.08
    èĸħ
    0.08
    åīįæĻ¯
    0.07
    Activations Density 0.036%

    No Known Activations