© 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. 32395
    Prev
    Next
    INDEX
    Explanations

    introduced or described

    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
    enz
    -0.08
    ä¹Łè®¸æĺ¯
    -0.08
    è¿ĺç®Ĺ
    -0.08
    大éĿ¢ç§¯
    -0.08
     ours
    -0.08
    éĻĭ
    -0.08
    Pro
    -0.08
    DCF
    -0.08
    åı£æ°Ķ
    -0.08
    UTH
    -0.07
    POSITIVE LOGITS
     wÅĤaÅĽnie
    0.14
     именно
    0.12
     بÙĩØ°Ùĩ
    0.12
    è¿Ļç§įäºĭæĥħ
    0.11
    è¿Ļç§į
    0.11
    以æѤ
    0.11
    è¿Ļ个èģĮä¸ļ
    0.10
    æīĵå¼Ģ
    0.10
    éĢĻ種
    0.10
    ä»İæѤ
    0.10
    Activations Density 0.574%

    No Known Activations