© 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. 40336
    Prev
    Next
    INDEX
    Explanations

    daylight, daycare, Daytona, dream

    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
    ited
    -0.10
     Haram
    -0.10
    duc
    -0.09
    涧
    -0.09
    éĴī
    -0.08
    AIN
    -0.08
    би
    -0.08
    åĴĮæľįåĬ¡
    -0.08
    odge
    -0.08
    严å¯Ĩ
    -0.08
    POSITIVE LOGITS
    OfWeek
    0.12
    OfMonth
    0.11
    iful
    0.10
    worm
    0.10
    ãĤĪãģĨãģª
    0.10
     mắn
    0.10
    uate
    0.09
    ä¸įåħĭ
    0.09
    inka
    0.09
    dream
    0.09
    Activations Density 0.015%

    No Known Activations