© 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. 61364
    Prev
    Next
    INDEX
    Explanations

    professor emeritus

    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
    erman
    -0.09
    onth
    -0.09
    æĻĭåįĩ
    -0.08
    Neo
    -0.08
    éĿĽ
    -0.08
    éĢĨ转
    -0.08
    passport
    -0.08
     ance
    -0.08
    mong
    -0.07
    enn
    -0.07
    POSITIVE LOGITS
    æ¦Ķ
    0.10
    ä¿ĿæĮģçĿĢ
    0.10
    ä¸Ńå¤ĸ
    0.10
    çŃļ
    0.09
    ships
    0.09
    è¾£
    0.09
    åĢ¬
    0.09
    çľ¼ç§ij
    0.09
    è¾īçħĮ
    0.09
    aldi
    0.09
    Activations Density 0.007%

    No Known Activations