© 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. 40192
    Prev
    Next
    INDEX
    Explanations

    incident occurrence

    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
    wart
    -0.11
    ings
    -0.10
    -0.10
    inh
    -0.09
    .googleapis
    -0.09
    coming
    -0.09
    ander
    -0.09
    èĥ¥
    -0.09
    侬
    -0.09
    ãģ£ãģįãĤĬ
    -0.09
    POSITIVE LOGITS
    Occurred
    0.12
    uality
    0.11
    çļĦåıijçĶŁ
    0.10
    ç°¿
    0.09
    亵
    0.09
    س
    0.09
    ally
    0.09
    涯
    0.09
    ات
    0.09
    cy
    0.09
    Activations Density 0.009%

    No Known Activations