© 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. 60690
    Prev
    Next
    INDEX
    Explanations

    nonprofit Austin research game television international restaurant

    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
    Negative Logits
     irre
    -0.08
    大éĺŁ
    -0.08
    è½»è½»åľ°
    -0.08
    andal
    -0.08
    -office
    -0.07
    /devices
    -0.07
    guns
    -0.07
    éĨĴæĿ¥
    -0.07
    åĪĴ
    -0.07
    _subs
    -0.07
    POSITIVE LOGITS
    çģ¯ç¬¼
    0.10
    éļ¶å±ŀäºİ
    0.10
    éĴ¤
    0.09
    ä¼łåĩº
    0.09
    umm
    0.09
    è´Łè´£ä»»
    0.09
    å¿ĸ
    0.09
    çļĦä¸Ģç§į
    0.09
    æ³ķå¾ĭ责任
    0.09
    æĬ¡
    0.09
    Activations Density 0.078%

    No Known Activations