© 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. 16800
    Prev
    Next
    INDEX
    Explanations

    citations or licensing

    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
    æľ¦èĥ§
    -0.12
    æ·±åĪ»çļĦ
    -0.10
    ä¸įåĬ¨
    -0.09
    uries
    -0.09
    éĢł
    -0.09
    åħ¥åľº
    -0.09
    è¿ĩåħ³
    -0.08
    èĩªå®¶
    -0.08
    åįķ身
    -0.08
    ãĥĥãĤ·
    -0.08
    POSITIVE LOGITS
     Flint
    0.10
    æĭ³å¤´
    0.09
    ç¬ij声
    0.09
    èľĹ
    0.08
    åĮĸè¿Ľç¨ĭ
    0.08
    weigh
    0.08
    stants
    0.08
    isle
    0.08
    ä¸ŃåĽ½å¤§éĻĨ
    0.08
    å¯Ĩ
    0.08
    Activations Density 0.178%

    No Known Activations