© 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. 12158
    Prev
    Next
    INDEX
    Explanations

    and followed by names or descriptions

    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
    çıIJ
    -0.11
    åĺīå¹´åįİ
    -0.10
    ersh
    -0.10
    å¼Ĥåľ°
    -0.09
    åºĻ
    -0.09
    为ä¸ŃåĽ½
    -0.09
    讽
    -0.09
    åĵĦ
    -0.09
    chor
    -0.08
    è½»è½»åľ°
    -0.08
    POSITIVE LOGITS
    iams
    0.09
    åģ¥
    0.09
     Trophy
    0.08
    ä¾ĿéĿł
    0.08
     Rack
    0.08
    è¿Ļåħ¶ä¸Ń
    0.08
     Shirt
    0.08
    ault
    0.08
    è¿ĻæĿ¡
    0.08
    tp
    0.08
    Activations Density 0.104%

    No Known Activations