© 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. 57486
    Prev
    Next
    INDEX
    Explanations

    officer, Inc., Interactive, Children

    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
    aux
    -0.08
    ivi
    -0.08
    heads
    -0.08
     ÑĢеалÑĮно
    -0.08
    éĿ¢å¯¹éĿ¢
    -0.08
    аÑĢа
    -0.08
    ND
    -0.08
    SOLE
    -0.08
    çļ¿
    -0.08
    Field
    -0.07
    POSITIVE LOGITS
    椿
    0.11
    ÑģÑĤÑĢ
    0.09
    åĿ¡
    0.09
    asel
    0.09
    è£Ĩ
    0.09
    ä¿Ŀè¯ģ
    0.09
    æľĢå¿«
    0.09
    ucha
    0.09
    .Reader
    0.09
    سد
    0.09
    Activations Density 0.003%

    No Known Activations