© 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. 62305
    Prev
    Next
    INDEX
    Explanations

    outline, contour, shape, boundary

    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
    追éĹ®
    -0.10
    夹
    -0.10
    èľĩ
    -0.08
    潮湿
    -0.08
    adians
    -0.08
    ouncer
    -0.08
    éģĭçĶ¨
    -0.08
    å²Ķ
    -0.08
    ellung
    -0.08
    宫
    -0.08
    POSITIVE LOGITS
    è½®å»ĵ
    0.25
     outline
    0.15
     outlines
    0.14
     contours
    0.13
     shape
    0.12
    outline
    0.12
    线æĿ¡
    0.10
    shape
    0.10
    æ¡Ĩæŀ¶
    0.10
     silhouette
    0.10
    Activations Density 0.062%

    No Known Activations