© 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. 32157
    Prev
    Next
    INDEX
    Explanations

    schizophrenia

    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
    è¼
    -0.10
    æIJª
    -0.09
    çķı
    -0.09
    纯
    -0.09
     Steele
    -0.09
    è¾Ħ
    -0.09
    éĢŁçİĩ
    -0.08
    osal
    -0.08
    ;amp
    -0.08
    ä»ĸçŁ¥éģĵ
    -0.08
    POSITIVE LOGITS
     Naming
    0.09
    _launch
    0.09
    .nlm
    0.08
    æľī趣çļĦ
    0.08
    enity
    0.08
    jiang
    0.08
    grim
    0.08
    ocht
    0.08
    翱
    0.08
    iaz
    0.08
    Activations Density 0.170%

    No Known Activations