© 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. 897
    Prev
    Next
    INDEX
    Explanations

    over, side, turn, flip

    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
    uml
    -0.09
    วย
    -0.09
    åIJĪçIJĨçļĦ
    -0.08
    èµ°åľ¨
    -0.08
    ç«ĭå¿Ĺ
    -0.08
    ä¸Ŀ毫
    -0.08
    .jackson
    -0.08
    spy
    -0.08
    é«ĺæķĪçļĦ
    -0.08
    ä¹ŁåĽłæѤ
    -0.08
    POSITIVE LOGITS
    ç¿»
    0.11
    ä¸ĢéĿ¢
    0.10
    åİŁæĿ¥
    0.10
     пеÑĢев
    0.10
    æīĴ
    0.09
    =log
    0.09
    _uniform
    0.09
    าà¸ĩ
    0.09
    æ¯ı个人éĥ½
    0.09
    åİŁæĿ¥çļĦ
    0.09
    Activations Density 0.005%

    No Known Activations