© 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. 6065
    Prev
    Next
    INDEX
    Explanations

    Y.M.C.A., CSIRO, MCA, RCMP, CA

    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
    elman
    -0.10
    ARAM
    -0.09
    изаÑĨиÑı
    -0.09
    ä¸įéĶĪ
    -0.09
    asure
    -0.09
     напÑĢавлен
    -0.09
    IBLE
    -0.09
    大éĺŁ
    -0.08
    yrı
    -0.08
    imon
    -0.08
    POSITIVE LOGITS
    è··
    0.09
    å¤©çľŁ
    0.08
    eras
    0.08
    æıIJåĢ¡
    0.08
    -president
    0.08
    agh
    0.07
     tactical
    0.07
    tran
    0.07
    enen
    0.07
    åī¿
    0.07
    Activations Density 0.002%

    No Known Activations