© 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. 63827
    Prev
    Next
    INDEX
    Explanations

    1 tablespoon

    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
    æłĩéħį
    -0.10
    odore
    -0.10
    á»ijt
    -0.09
    ìĥµ
    -0.09
    estic
    -0.09
     Modi
    -0.09
    çĶ¨èĩªå·±çļĦ
    -0.09
    antal
    -0.09
    _ACTIV
    -0.09
     onDataChange
    -0.08
    POSITIVE LOGITS
    èĻ±
    0.09
    леÑĩ
    0.09
    hack
    0.09
    æ¯ĵ
    0.08
    ç»ĵåIJĪèµ·æĿ¥
    0.08
    ترÙĪ
    0.08
    çħ¨
    0.08
    çķĻä½ı
    0.08
    æ°¡
    0.08
    ä¸Ģåı¥è¯Ŀ
    0.08
    Activations Density 0.065%

    No Known Activations