© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 29764
    Prev
    Next
    INDEX
    Explanations

    Copyright (

    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
    èĻļ
    -0.09
    马æĿ¥
    -0.09
    使çĶ¨ç¶²è·¯
    -0.09
    æ·¡æ·¡
    -0.08
    emm
    -0.08
    ulist
    -0.08
    _Mod
    -0.08
    влад
    -0.08
    оÑī
    -0.08
    ä¸Ģ次次
    -0.08
    POSITIVE LOGITS
    çĤ¬
    0.09
    绥
    0.09
    orton
    0.08
    isos
    0.08
    é»Ŀ
    0.08
    çħĬ
    0.08
    _AXIS
    0.08
    ä¹Ŀæ±Ł
    0.08
    浸
    0.08
    åIJ¬è¯¾
    0.08
    Activations Density 0.018%

    No Known Activations