© 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. 2312
    Prev
    Next
    INDEX
    Explanations

    color, colors, shades

    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
    åŀĤ
    -0.09
    åĬ¡å·¥
    -0.09
    éĴ±è´¢
    -0.09
    èĩ´çĶµ
    -0.09
    治好
    -0.09
    å¿ĻçĿĢ
    -0.09
    å¤ĩèĢĥ
    -0.08
    秣
    -0.08
    é¦Ĵ头
    -0.08
     prec
    -0.08
    POSITIVE LOGITS
    é¢ľèī²
    0.22
    çļĦé¢ľèī²
    0.21
    èī²
    0.21
     color
    0.19
    èī²å½©
    0.18
     colors
    0.17
    color
    0.16
    Color
    0.16
    .color
    0.16
     Color
    0.16
    Activations Density 0.257%

    No Known Activations