© 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. 61758
    Prev
    Next
    INDEX
    Explanations

    full-color artwork

    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
    鬻
    -0.09
    ä»İèĢĮ
    -0.09
    æµģ浪
    -0.09
    ãĤ·ãĥ§
    -0.09
    .twig
    -0.09
    toFixed
    -0.08
    æīĢå±ŀ
    -0.08
    å¡ijéĢł
    -0.08
    æĴŃ
    -0.08
     Bain
    -0.08
    POSITIVE LOGITS
    é²ľèī³
    0.16
    彩èī²
    0.16
    é¢ľèī²
    0.15
    èī²å½©
    0.15
     color
    0.14
     colors
    0.14
    -color
    0.14
    èī²
    0.14
    çļĦé¢ľèī²
    0.13
    èī³
    0.13
    Activations Density 0.070%

    No Known Activations