© 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. 48902
    Prev
    Next
    INDEX
    Explanations

    most listed/recorded/sold/voted/cultivated/prescribed

    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
    èĢģå®ŀ
    -0.09
    jspx
    -0.09
    æŀģéĻIJ
    -0.08
    ç»Ģ
    -0.08
    çļĦ认è¯Ĩ
    -0.08
    /TR
    -0.08
    _IDS
    -0.08
    éĵī
    -0.08
    _FAR
    -0.08
    èĤª
    -0.08
    POSITIVE LOGITS
    çļĦä¸ĢéĿ¢
    0.10
    åħ¶æ¬¡æĺ¯
    0.10
    åİŁåĽłä¹ĭä¸Ģ
    0.10
    é¢ijç¹ģ
    0.09
    åĦ¿ç«¥
    0.09
    æ¦ľ
    0.09
    æľĢå¤ļçļĦ
    0.09
    ä¸Ģæĸ¹éĿ¢æĺ¯
    0.09
    çħŀ
    0.08
    ool
    0.08
    Activations Density 0.103%

    No Known Activations