© 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. 24213
    Prev
    Next
    INDEX
    Explanations

    incidence of

    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
    Negative Logits
    .ascii
    -0.10
    è±¢
    -0.10
    ings
    -0.10
    wart
    -0.09
    æģ«
    -0.09
    warts
    -0.09
    æĴķ
    -0.09
    INGS
    -0.09
    éĿ¥
    -0.09
    ãģıãĤĮ
    -0.09
    POSITIVE LOGITS
    uate
    0.12
    lei
    0.10
    uation
    0.10
    cy
    0.09
    ç°¿
    0.09
     dÄ±ÅŁÄ±
    0.09
    ories
    0.09
    lá
    0.08
    urr
    0.08
    òn
    0.08
    Activations Density 0.026%

    No Known Activations