© 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. 16598
    Prev
    Next
    INDEX
    Explanations

    reprimand, admonish, rebuke

    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
    å°±è·Ł
    -0.09
    timeline
    -0.09
    esto
    -0.09
    ControlEvents
    -0.08
    Ãłi
    -0.08
    SimpleName
    -0.08
    uilt
    -0.08
     saf
    -0.08
    å¯Ŀ
    -0.08
    .pad
    -0.08
    POSITIVE LOGITS
    æĸ¥
    0.11
    èĢģå®ŀ
    0.10
    esy
    0.10
    æķĻè®Ń
    0.10
    éĶ¢
    0.10
    åľºéĿ¢
    0.09
    æķ´é¡¿
    0.09
    æĮĩè´£
    0.09
    éŀŃ
    0.09
    볨
    0.09
    Activations Density 0.009%

    No Known Activations