© 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. 60556
    Prev
    Next
    INDEX
    Explanations

    free software license

    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
    箪
    -0.08
    æĸ¹å¼ıè¿Ľè¡Į
    -0.08
    à¸Ńม
    -0.08
    _DESTROY
    -0.08
    nik
    -0.08
    建çŃijéĿ¢ç§¯
    -0.08
    å®ŀæĸ½æĦıè§ģ
    -0.08
    ouver
    -0.08
    éĹª
    -0.08
     Garner
    -0.08
    POSITIVE LOGITS
    çĬĩ
    0.10
    åĢĴ
    0.09
    поÑĤÑĢеб
    0.09
    zee
    0.09
    icity
    0.09
    纳æĸ¯
    0.09
    etta
    0.08
    ENCH
    0.08
    éĿ¢æĿ¡
    0.08
    äºĶä¸Ģ
    0.08
    Activations Density 0.014%

    No Known Activations