© 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. 12071
    Prev
    Next
    INDEX
    Explanations

    migration and movement

    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
    ä¸įä¸ĭ
    -0.12
    enton
    -0.10
     Graves
    -0.09
    UserRole
    -0.09
    azo
    -0.09
    ç»Ŀ大å¤ļæķ°
    -0.09
    åłĤ
    -0.09
    ä¸ĭä¸Ģ代
    -0.09
    æģ¶åĬ£
    -0.09
    åĪ©çĶ¨çİĩ
    -0.08
    POSITIVE LOGITS
    èĢħçļĦ
    0.10
    åŁİå¸Ĥ管çIJĨ
    0.10
    lÃŃ
    0.09
    adel
    0.09
    éģĵ士
    0.09
    注æĺİåĩºå¤Ħ
    0.08
    æŃ£åĽłä¸º
    0.08
    è¶ĭåĬ¿
    0.08
    ä¸Ī
    0.08
    èļ©
    0.08
    Activations Density 0.168%

    No Known Activations