© 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. 60569
    Prev
    Next
    INDEX
    Explanations

    analyst or analysts

    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
    ality
    -0.11
    çĦ¶æĺ¯
    -0.09
    æł·åŃIJ
    -0.09
    lain
    -0.09
    /from
    -0.09
    bies
    -0.09
     Äijá»±ng
    -0.08
    veal
    -0.08
    standing
    -0.08
    BOSE
    -0.08
    POSITIVE LOGITS
    å¼ĢæĿ¥
    0.10
    веÑĢ
    0.10
    igator
    0.10
    éĺŁä¼į建设
    0.10
    çļĦ缮åħī
    0.09
    ÙĪص
    0.09
    egin
    0.09
    urally
    0.09
    ervice
    0.09
    irector
    0.09
    Activations Density 0.004%

    No Known Activations