© 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. 40285
    Prev
    Next
    INDEX
    Explanations

    rat studies

    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
    arily
    -0.10
    à¹Ģà¸Ńà¸ĩ
    -0.09
    æģIJ
    -0.09
    ازÙĬ
    -0.09
    大éģĵ
    -0.09
    å¤ıæĹ¥
    -0.09
    eday
    -0.09
    teen
    -0.09
    affer
    -0.08
    ../../../
    -0.08
    POSITIVE LOGITS
    istic
    0.09
    é¼ł
    0.09
    tribute
    0.09
    lessly
    0.09
    ainment
    0.09
    æ¶İ
    0.09
    åģļ梦
    0.08
    ðŁı»
    0.08
    ormsg
    0.08
    ÑĤен
    0.08
    Activations Density 0.037%

    No Known Activations