© 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. 18526
    Prev
    Next
    INDEX
    Explanations

    area units

    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
    深交
    -0.10
    yor
    -0.10
    çīµ
    -0.09
    èł
    -0.09
    illet
    -0.08
    æ´ĭæ´ĭ
    -0.08
    æīĭä¸Ń
    -0.08
    ä¸ĢåIJį
    -0.08
    INGLE
    -0.08
     Jar
    -0.08
    POSITIVE LOGITS
    éĿ¢ç§¯
    0.13
    -area
    0.11
     area
    0.11
    æľīå¤ļ大
    0.10
    (area
    0.10
    æĢ»éĿ¢ç§¯
    0.10
    ä»Ĺ
    0.09
    çĸĻ
    0.09
    ä¸Ģçīĩ
    0.09
    éĿ¢ç§¯çº¦
    0.09
    Activations Density 0.111%

    No Known Activations