© 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. 32530
    Prev
    Next
    INDEX
    Explanations

    abusive or suicidal content

    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
    äºĨä¸įå°ij
    -0.11
    æļĿ
    -0.10
    ä¸Ģå®ļçļĦ
    -0.08
     Rebels
    -0.08
    ол
    -0.08
    çļ¿
    -0.08
    åijµ
    -0.08
    alis
    -0.08
    äºĨ许å¤ļ
    -0.08
    äºĨä¸Ģ个
    -0.08
    POSITIVE LOGITS
    ities
    0.11
    ness
    0.10
    itarian
    0.10
    æĭ³å¤´
    0.10
    OAD
    0.09
    éĮ¾
    0.09
    ä¸įå°½
    0.09
    hips
    0.09
    迫使
    0.09
    EIF
    0.08
    Activations Density 0.003%

    No Known Activations