© 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. 19284
    Prev
    Next
    INDEX
    Explanations

    unsupported browser messages

    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
    col
    -0.09
    RACT
    -0.08
    å¼ķçĪĨ
    -0.08
    cycles
    -0.08
    ç¿ĥ
    -0.08
    deep
    -0.08
    æıŃ
    -0.08
    èĪį
    -0.07
     Nope
    -0.07
     Lives
    -0.07
    POSITIVE LOGITS
    æĪĸèĢħ说
    0.10
    ä¸į代表
    0.09
     mas
    0.09
    类产åĵģ
    0.09
    夹
    0.09
    æĪIJé¾Ļ
    0.09
    é¦Ļæ°´
    0.08
    è·ŁæĪij
    0.08
    äºİæĺ¯æĪij
    0.08
    ãģ¨ãģĦãģĨãģ®ãģ¯
    0.08
    Activations Density 0.064%

    No Known Activations