© 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. 58672
    Prev
    Next
    INDEX
    Explanations

    burial or buried context

    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
    åĽ·
    -0.10
    bul
    -0.09
    ä¹Łä¸įæķ¢
    -0.08
    edu
    -0.08
    veau
    -0.08
     вÑĢемен
    -0.08
    ailed
    -0.08
    人为
    -0.08
    éĿ¢çĽ®
    -0.08
    IMUM
    -0.08
    POSITIVE LOGITS
    çıįçıł
    0.09
    лан
    0.09
    tie
    0.09
    åĪ¨
    0.09
    inati
    0.09
    tol
    0.09
    tem
    0.08
    渴
    0.08
    èĽ©
    0.08
    è¸Į
    0.08
    Activations Density 0.002%

    No Known Activations