© 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. 48569
    Prev
    Next
    INDEX
    Explanations

    jury decisions and verdicts

    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
    itud
    -0.10
    /up
    -0.10
    çIJĨä¼ļ
    -0.09
     вÑĢемен
    -0.09
    鸡汤
    -0.09
    iton
    -0.08
    urator
    -0.08
    æ°Ķ
    -0.08
    ç»ıæµİä½ĵ
    -0.08
    pus
    -0.08
    POSITIVE LOGITS
    ا
    0.10
    ing
    0.09
    iaz
    0.09
    oran
    0.09
    å¾Ĺä½ı
    0.08
    ä¹ĭä½ľ
    0.08
    åĪ«çļĦ
    0.08
    æ¥Ķ
    0.08
    winner
    0.08
    fold
    0.08
    Activations Density 0.004%

    No Known Activations