© 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. 29389
    Prev
    Next
    INDEX
    Explanations

    vote

    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
    ä¹Łä¸įè¦ģ
    -0.08
    æĬĬè¿ĻäºĽ
    -0.08
    âĦĺ
    -0.08
    å¯¹æľªæĿ¥
    -0.08
    ä¹īåĬ¡
    -0.08
     SOLD
    -0.08
    è¯Ŀ说
    -0.08
    DIR
    -0.08
    æį¢äºĨ
    -0.08
    éĢīæĭ
    -0.08
    POSITIVE LOGITS
    è®®æ¡Ī
    0.12
    amon
    0.11
    项
    0.10
    åħ³ä¹İ
    0.10
    触åıĬ
    0.10
    ä¹ĭäºĭ
    0.10
    äºĭ项
    0.10
    é¦Ĭ
    0.10
    éģŃåĪ°
    0.09
    úc
    0.09
    Activations Density 0.103%

    No Known Activations