© 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. 59158
    Prev
    Next
    INDEX
    Explanations

    a noun

    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
    Not in Any Lists

    No Comments

    Negative Logits
    æ»Ĥ
    -0.11
    ä¸İä¼Ĺ
    -0.09
    ades
    -0.09
    åıĮèħ¿
    -0.09
    _EV
    -0.09
    -Feb
    -0.09
    hammer
    -0.09
    GRA
    -0.09
     NRA
    -0.09
     ëĪĦ
    -0.08
    POSITIVE LOGITS
    客æĪ¿
    0.09
    æĪijå¸ĮæľĽ
    0.09
    cene
    0.08
    å°±æĺ¯ä¸Ģ个
    0.08
    åį·
    0.08
    çłĶåĪ¤
    0.08
    åŃĹ
    0.08
    "
    0.08
     ary
    0.08
    æ°¸
    0.08
    Activations Density 0.264%

    No Known Activations