© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 31372
    Prev
    Next
    INDEX
    Explanations

    weight, derivative, project, mixture

    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
    建åįİ
    -0.10
    åijķ
    -0.10
    oen
    -0.10
    Leap
    -0.09
    迤
    -0.09
    çĶļèĩ³æĺ¯
    -0.09
    masını
    -0.09
     Äijả
    -0.09
    寵
    -0.09
    ilst
    -0.09
    POSITIVE LOGITS
    åľ¨æ·±åľ³
    0.08
    åľ¨ä¸ĢæĹģ
    0.08
    æ´ĭæ´ĭ
    0.08
    icky
    0.08
    æĢ¥éĢŁ
    0.08
    inger
    0.07
     ebenfalls
    0.07
     prem
    0.07
    æĭ¿æĿ¥
    0.07
    æģļ
    0.07
    Activations Density 0.055%

    No Known Activations