© 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. 6218
    Prev
    Next
    INDEX
    Explanations

    can handle or could

    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
    人人éĥ½
    -0.10
    /inet
    -0.10
    chein
    -0.10
    å¦Ĥæľī
    -0.10
    å¾Īå¤ļäºĭæĥħ
    -0.09
    assage
    -0.09
    å¾Īå¤ļ
    -0.09
     Rena
    -0.09
    heim
    -0.09
    å¹²åĺĽ
    -0.08
    POSITIVE LOGITS
    åĬłä¹ĭ
    0.09
    ç¦ıå¾·
    0.08
    饱åĴĮ
    0.08
    uat
    0.08
    oki
    0.08
    è·Ľ
    0.08
    绵
    0.08
    ä¸įä¸ĭ
    0.08
    è°ĥéħį
    0.08
     mo
    0.08
    Activations Density 0.035%

    No Known Activations