© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7540
    Prev
    Next
    INDEX
    Explanations

    git pull request

    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
    iro
    -0.11
    zia
    -0.10
    uality
    -0.10
    ä¹İ
    -0.10
    imals
    -0.10
    ely
    -0.10
    ë£Į
    -0.09
    лад
    -0.09
    bour
    -0.09
    uales
    -0.09
    POSITIVE LOGITS
    æĭ¢
    0.10
    ong
    0.10
    backs
    0.10
    ä¸įå®ļ
    0.09
    igg
    0.09
    ang
    0.09
    angs
    0.09
    ìį¨
    0.09
    ucid
    0.09
    abor
    0.09
    Activations Density 0.018%

    No Known Activations