© 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. 18090
    Prev
    Next
    INDEX
    Explanations

    hair and body parts

    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
    æ¯ĽåŃĶ
    -0.09
    abor
    -0.09
    .fig
    -0.09
    /detail
    -0.08
    顺
    -0.08
    Browser
    -0.08
    èĢĨ
    -0.08
    æĻĮ
    -0.08
    .Detail
    -0.08
    æĻ´
    -0.08
    POSITIVE LOGITS
    ä½ĵçİ°
    0.09
     Glas
    0.08
    ograms
    0.08
    icle
    0.08
    dp
    0.08
     ExecutionContext
    0.08
    åIJģ
    0.08
    æ§İ
    0.08
    墨西åĵ¥
    0.08
    ä¹Ŀæ±Ł
    0.08
    Activations Density 0.013%

    No Known Activations