© 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. 56718
    Prev
    Next
    INDEX
    Explanations

    public hearing, health, art, information, relations, theater, education, instructor

    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
    é£İäºij
    -0.10
     Bauer
    -0.09
     Magazine
    -0.09
    COMMON
    -0.09
    ç¡®ç«ĭ
    -0.09
    inqu
    -0.09
    奢
    -0.09
    æĭĸæ¬ł
    -0.08
     unp
    -0.08
    æľ
    -0.08
    POSITIVE LOGITS
    访
    0.10
    å¾Ĵ
    0.10
    inker
    0.08
    å·¥ä½ľèĢħ
    0.08
    ogl
    0.08
    éĻĢ
    0.08
    itas
    0.08
     boo
    0.08
    -grade
    0.08
    atron
    0.08
    Activations Density 0.015%

    No Known Activations