© 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. 4402
    Prev
    Next
    INDEX
    Explanations

    HTML tags and URLs

    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
    ä¸ĭä¸Ģç¯ĩ
    -0.08
    -0.08
     Gonzalez
    -0.08
    轶
    -0.07
     mạch
    -0.07
    ï¸ı
    -0.07
    ç¯ĩ
    -0.07
    è¦ĨçĽĸéĿ¢
    -0.07
    ï¼Ĭ
    -0.07
    å½±åĵįåĬĽ
    -0.07
    POSITIVE LOGITS
    èĢĨ
    0.11
    ancement
    0.10
    apsed
    0.09
    èĽĩ
    0.09
    è¿Ļåı¥è¯Ŀ
    0.09
    骥
    0.09
    æµĵæµĵ
    0.09
    rais
    0.09
     Hitch
    0.09
    æĽ´æ·±
    0.09
    Activations Density 0.001%

    No Known Activations