© 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. 31251
    Prev
    Next
    INDEX
    Explanations

    list item separators

    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
    ç¿®
    -0.11
    odon
    -0.09
    ondo
    -0.09
    åĢº
    -0.09
    lander
    -0.09
    åĪĿ
    -0.09
    cono
    -0.09
    brook
    -0.08
    esser
    -0.08
    egr
    -0.08
    POSITIVE LOGITS
    æĪIJåĵģ
    0.11
    ä¸įçķĻ
    0.10
    elo
    0.09
    èµ°åĩº
    0.09
    issor
    0.09
    ä¸įå°ıå¿ĥ
    0.09
     puss
    0.08
     answers
    0.08
    ç²¾èĭ±
    0.08
    å¢ŀ强äºĨ
    0.08
    Activations Density 0.001%

    No Known Activations