© 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. 6299
    Prev
    Next
    INDEX
    Explanations

    middle or balance

    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
     обоÑĢ
    -0.09
    éĢĨ
    -0.09
    èĤĨ
    -0.08
    æĻļ
    -0.08
    omorphic
    -0.08
    onders
    -0.08
    æĿ¥çĶµ
    -0.08
    lick
    -0.08
    <!--[
    -0.08
    æľŁæľ«
    -0.07
    POSITIVE LOGITS
    ä¸ŃéĹ´
    0.17
    平衡
    0.15
    utral
    0.14
     middle
    0.13
    .middle
    0.13
    _MIDDLE
    0.13
    -middle
    0.12
    middle
    0.12
     Balance
    0.11
    第ä¸īæĸ¹
    0.11
    Activations Density 0.062%

    No Known Activations