© 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. 59084
    Prev
    Next
    INDEX
    Explanations

    license or legal text elements

    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
    ç»ıæµİæĬĢæľ¯
    -0.10
    é¢Ŀå¤ĸ
    -0.09
    åIJ¬åIJ¬
    -0.09
    æ´ģçĻ½
    -0.09
    å®£ä¼łæķĻèĤ²
    -0.09
    éĹ®éĹ®
    -0.09
    ç©°
    -0.09
    aub
    -0.09
    çļĦ人çĶŁ
    -0.09
     Aub
    -0.09
    POSITIVE LOGITS
    Nam
    0.09
     ÑĢаÑģÑģмаÑĤÑĢ
    0.08
    oho
    0.08
     Nam
    0.08
    lean
    0.08
    河西
    0.08
    çĽĨ
    0.08
    <::
    0.07
     Frances
    0.07
     Misc
    0.07
    Activations Density 0.168%

    No Known Activations