© 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. 6144
    Prev
    Next
    INDEX
    Explanations

    Bible verses and dates

    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
    ugh
    -0.09
    esch
    -0.08
    www
    -0.07
     front
    -0.07
    front
    -0.07
    tim
    -0.07
    åľ¨åħ¶
    -0.07
    æŃ£éĿ¢
    -0.07
    ÑĢай
    -0.07
    sf
    -0.07
    POSITIVE LOGITS
    amu
    0.10
    åī¥
    0.10
    æĵĤ
    0.09
    /std
    0.09
    å·¥å§Ķ
    0.09
    ä¸Ńå¿ĥåŁİå¸Ĥ
    0.08
    èĩªçĦ¶çķĮ
    0.08
    ropp
    0.08
    Streamer
    0.08
    éĽĨèģļ
    0.08
    Activations Density 0.041%

    No Known Activations