© 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. 725
    Prev
    Next
    INDEX
    Explanations

    Site of Special Scientific

    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
    ittings
    -0.09
    åĮĹè·¯
    -0.09
    å±ĭéĩĮ
    -0.08
    èĩ´
    -0.08
    éºĵ
    -0.08
    好åIJĹ
    -0.08
    èĢIJ磨
    -0.08
    鼷éĶĭ
    -0.08
    åIJİåĭ¤
    -0.08
     Customs
    -0.08
    POSITIVE LOGITS
     демо
    0.10
     Sites
    0.10
    éģĹ产
    0.09
    ä¹¡åľŁ
    0.09
    çļĦæł¸å¿ĥ
    0.09
    ValueHandling
    0.09
    åĪĽæĸ°åŀĭ
    0.09
     иÑģ
    0.09
    éĿŀçī©è´¨
    0.08
    èµ·åĪĿ
    0.08
    Activations Density 0.122%

    No Known Activations