© 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. 26273
    Prev
    Next
    INDEX
    Explanations

    place names ending in ica/eca/onta/ia

    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
    æ¯Ķäºļ
    -0.10
    饺
    -0.09
    ission
    -0.09
    elves
    -0.09
    å¤ķéĺ³
    -0.09
    å¯Ĥå¯ŀ
    -0.09
    æĬ¤èº«
    -0.09
    人æµģ
    -0.08
    inst
    -0.08
    éŀł
    -0.08
    POSITIVE LOGITS
    bens
    0.10
    ç¨
    0.09
    主è¦ģåİŁåĽł
    0.09
    窳
    0.08
    laden
    0.08
    hair
    0.08
    bor
    0.08
    _NOP
    0.08
    éĿŀæ³ķ
    0.08
    ä¸įå¦Ĥ
    0.08
    Activations Density 0.006%

    No Known Activations