© 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. 60552
    Prev
    Next
    INDEX
    Explanations

    man and mankind

    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
    åĬ¿å¤´
    -0.09
    ched
    -0.09
    æīĵåĬ¨
    -0.09
    ipc
    -0.08
    uche
    -0.08
    tero
    -0.08
    emm
    -0.08
    å¸ĤåĢ¼
    -0.08
    ceive
    -0.08
    彦
    -0.08
    POSITIVE LOGITS
    çIJĨæĢ§
    0.09
    ç§ijåѦåıijå±ķ
    0.09
     mates
    0.09
    ä¸ĩçī©
    0.09
    å°¤åħ¶æĺ¯
    0.09
    æģ¯æģ¯
    0.08
    è¿ĻæĿ¡è·¯
    0.08
    ankind
    0.08
    ugu
    0.08
     busiest
    0.08
    Activations Density 0.027%

    No Known Activations