© 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. 19062
    Prev
    Next
    INDEX
    Explanations

    opus numbers and composers

    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
    iteral
    -0.10
    人士
    -0.10
    æ°Ķæģ¯
    -0.08
    owitz
    -0.08
    è´©
    -0.08
    ì°½
    -0.08
    ervative
    -0.08
    饮
    -0.08
    çıŃéķ¿
    -0.08
    .DataTable
    -0.08
    POSITIVE LOGITS
    æijŀ
    0.10
    ÑģÑĤÑĭ
    0.09
    áĢī
    0.09
    æ¢ĥ
    0.09
    ||(
    0.08
    æĥĬ
    0.08
    .dex
    0.08
    idor
    0.08
    keley
    0.08
    ymes
    0.08
    Activations Density 0.031%

    No Known Activations