© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 24006
    Prev
    Next
    INDEX
    Explanations

    Bosch Software, shop around/for, impact tool

    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
    SES
    -0.10
    oons
    -0.09
     пÑĢедоÑģÑĤавлен
    -0.09
    gü
    -0.09
    arks
    -0.08
    -angular
    -0.08
    edicine
    -0.08
    istol
    -0.08
    (sess
    -0.08
    ä»İå°ı
    -0.08
    POSITIVE LOGITS
    teen
    0.09
    çį¸
    0.08
    ç¬ı
    0.08
    YA
    0.08
    èĽĩ
    0.08
    à¹Į
    0.08
    ä¹ĭ乡
    0.08
    iken
    0.08
    辦
    0.08
    åħij
    0.08
    Activations Density 0.003%

    No Known Activations