© 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. 26329
    Prev
    Next
    INDEX
    Explanations

    manage users and data

    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
    èĩªå¸¦
    -0.11
    ARY
    -0.09
     tiá»ģm
    -0.08
    _STRIP
    -0.08
    alk
    -0.08
    proved
    -0.08
    æľīæľºä¼ļ
    -0.08
    enis
    -0.08
    .scheme
    -0.08
    ä¸įä¸Ģå®ļ
    -0.08
    POSITIVE LOGITS
    管çIJĨåĴĮ
    0.13
    管çIJĨ
    0.12
     manage
    0.12
     manages
    0.10
     managing
    0.10
    manage
    0.10
    /manage
    0.10
    ê´Ģ리
    0.09
     Manage
    0.09
     quản
    0.09
    Activations Density 0.107%

    No Known Activations