© 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. 12277
    Prev
    Next
    INDEX
    Explanations

    face of

    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
    èĩªåľ¨
    -0.10
    ä¸įä¸ĭ
    -0.09
    _fwd
    -0.09
    强壮
    -0.09
    ucch
    -0.08
    禹
    -0.08
    itel
    -0.08
     Matth
    -0.08
    åĩºæīĭ
    -0.08
    cue
    -0.08
    POSITIVE LOGITS
    形象
    0.11
    éĿ¢åŃĶ
    0.11
    Faces
    0.10
    ç½¢äºĨ
    0.10
    å¾ģæ±Ĥ
    0.09
     faces
    0.09
    æ··ä¹±
    0.09
    ä¸İæŶ
    0.09
    ç¯Ļ
    0.09
    åĴĮå®ĮåĸĦ
    0.09
    Activations Density 0.021%

    No Known Activations