© 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. 18088
    Prev
    Next
    INDEX
    Explanations

    scrub

    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
    绩
    -0.10
    .Pixel
    -0.09
    odor
    -0.09
    สมาà¸Ĭ
    -0.08
    asy
    -0.08
    idon
    -0.08
     Morm
    -0.08
     hÆ°á»Łng
    -0.08
    ัà¸Ķ
    -0.08
    /end
    -0.08
    POSITIVE LOGITS
    äºĨåįĬ天
    0.10
    ä½ļ
    0.10
    äºĨä¸Ģä¸ĭ
    0.10
    ä¸įå·²
    0.09
    ç¾¤å²Ľ
    0.09
    éģį
    0.09
    lands
    0.09
    è¿ĩçļĦ
    0.09
    ä¸įåĩºæĿ¥
    0.09
    athing
    0.08
    Activations Density 0.003%

    No Known Activations