© 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. 26061
    Prev
    Next
    INDEX
    Explanations

    person who became

    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
    åĽłä¸ºä»ĸ
    -0.10
    æĥħåĨµæĿ¥çľĭ
    -0.10
    å¼ıçļĦ
    -0.08
    ä»İåݻ年
    -0.08
    ymm
    -0.08
     lẫn
    -0.08
    èĻ½çĦ¶æĺ¯
    -0.08
    äººåľ¨
    -0.08
    ä¸İä¸ŃåĽ½
    -0.08
    Fatal
    -0.08
    POSITIVE LOGITS
    _SCL
    0.10
    ajs
    0.09
    çĥ
    0.09
     Hob
    0.09
    èİ«è¿ĩäºİ
    0.09
    uality
    0.09
    è¯İ
    0.09
    amy
    0.09
    scp
    0.08
    ueue
    0.08
    Activations Density 0.258%

    No Known Activations