© 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. 57603
    Prev
    Next
    INDEX
    Explanations

    balls, derivatives, lottery

    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
    tero
    -0.09
     здоÑĢов
    -0.08
    alty
    -0.08
    款
    -0.08
    iones
    -0.08
    嵯
    -0.08
    ihan
    -0.08
    ãİŀ
    -0.08
    飯
    -0.08
    表述
    -0.08
    POSITIVE LOGITS
    zac
    0.09
    é£İåı£
    0.09
     Hã
    0.09
    hoff
    0.09
    infer
    0.09
    week
    0.09
    yü
    0.09
    fan
    0.08
     пÑıÑĤ
    0.08
    çĸ«æĥħå½±åĵį
    0.08
    Activations Density 0.001%

    No Known Activations