© 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. 59230
    Prev
    Next
    INDEX
    Explanations

    lists, punctuation, or clauses

    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
    äºİæĺ¯æĪij
    -0.10
    åľ£åľ°
    -0.10
    ä½Ĩåį´
    -0.09
    åľ°æłĩ
    -0.09
    管çIJĨå±Ĥ
    -0.09
    èľľ
    -0.09
    èĢģçīĮ
    -0.09
    çİ°åľ¨å·²ç»ı
    -0.09
    ä¸Ģå°ģ
    -0.09
    åıijå±ķéĺ¶æ®µ
    -0.09
    POSITIVE LOGITS
     конеÑĩно
    0.09
    浯
    0.09
    iddy
    0.08
    ì²Ļ
    0.08
    æĶ
    0.08
    imeter
    0.08
    hra
    0.08
    _NEXT
    0.08
     Depot
    0.08
    andel
    0.08
    Activations Density 0.168%

    No Known Activations