© 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. 63991
    Prev
    Next
    INDEX
    Explanations

    antolia, vestigial, seamly, lobectomy, rugby, nippon

    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
    å½ĵä¹ĭ
    -0.09
    sic
    -0.09
    itr
    -0.09
    rium
    -0.09
    PLEX
    -0.09
     duyá»ĩt
    -0.09
    人士
    -0.08
    fre
    -0.08
    çļĦ空éĹ´
    -0.08
    宪
    -0.08
    POSITIVE LOGITS
    ted
    0.10
    gence
    0.10
    less
    0.09
    leted
    0.09
    dings
    0.09
    累累
    0.09
    èĥ³
    0.09
    unft
    0.08
    teen
    0.08
    sets
    0.08
    Activations Density 0.188%

    No Known Activations