© 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. 40420
    Prev
    Next
    INDEX
    Explanations

    under one roof

    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
    alto
    -0.10
    çĽ¸ä¼´
    -0.10
    涯
    -0.09
    onde
    -0.09
    æĴŀ
    -0.09
    åĭ¤
    -0.09
    çĶ«
    -0.09
    .sig
    -0.09
    çļĦåĪ°æĿ¥
    -0.09
    (UUID
    -0.09
    POSITIVE LOGITS
    ä¼ŀ
    0.09
    /runtime
    0.09
    whelming
    0.09
    est
    0.09
    neath
    0.09
    ania
    0.09
    é£İ鼨
    0.08
    åIJĮä¸Ģ个
    0.08
    /at
    0.08
    å¿«è¦ģ
    0.08
    Activations Density 0.073%

    No Known Activations