© 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. 16922
    Prev
    Next
    INDEX
    Explanations

    seen. or see

    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
    Not in Any Lists

    No Comments

    Negative Logits
    æ°´æĻ¶
    -0.10
    éĿŀåĩ¡
    -0.09
    è¿Ļä¸ĢçĤ¹
    -0.09
    çŀ
    -0.08
    ãģ¨ãģĦãģ£ãģ¦
    -0.08
    å£ģ纸
    -0.08
    èī°éļ¾
    -0.08
     Ñĩел
    -0.08
    人å±ħ
    -0.08
    åĽ½å®¶æĪĺçķ¥
    -0.08
    POSITIVE LOGITS
    èĢĨ
    0.09
    åģļ强
    0.09
     Allen
    0.08
     Gda
    0.08
    oor
    0.08
    è¯Ħè®®
    0.08
    urg
    0.08
    ÐIJÐĿ
    0.08
    -eyed
    0.08
    çªľ
    0.08
    Activations Density 0.036%

    No Known Activations