© 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. 40166
    Prev
    Next
    INDEX
    Explanations

    trout or Becker

    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
    ity
    -0.10
    nection
    -0.09
    ized
    -0.09
    ised
    -0.09
    ä½Ĺ
    -0.09
    ä¹ĵ
    -0.08
    大
    -0.08
    ulous
    -0.08
    ãĥ³ãĤ°
    -0.08
    çĵ¯
    -0.08
    POSITIVE LOGITS
    iest
    0.11
    ãģįãģŁ
    0.09
    sel
    0.09
    çļij
    0.09
    ening
    0.09
    ahead
    0.09
    ishly
    0.09
    ëŁī
    0.09
    manship
    0.09
    side
    0.09
    Activations Density 0.002%

    No Known Activations