© 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. 62096
    Prev
    Next
    INDEX
    Explanations

    for you / me

    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
    è½®
    -0.10
    èĬ½
    -0.09
    è½®æµģ
    -0.09
    _procs
    -0.08
    nist
    -0.08
    Charsets
    -0.08
    +-+-+-+-
    -0.08
    æľīå¾Ī大çļĦ
    -0.08
    æĬĬèĩªå·±çļĦ
    -0.08
    apan
    -0.08
    POSITIVE LOGITS
    帮ä»ĸ
    0.16
    ãģıãĤĮ
    0.11
    æĽ¿
    0.11
    ä¸ºä½ł
    0.10
    帮æĪij
    0.10
    帮å¿Ļ
    0.10
    帮
    0.10
     ÙĦÙĩÙħ
    0.10
    为æĤ¨
    0.10
    å¸®ä½ł
    0.10
    Activations Density 0.080%

    No Known Activations