© 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. 29644
    Prev
    Next
    INDEX
    Explanations

    level, magnitude, size, balance

    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
    jin
    -0.09
     инÑĤеÑĢÑĮеÑĢ
    -0.09
    çĨ±
    -0.08
    çĥŃ
    -0.08
    æºIJæºIJä¸įæĸŃ
    -0.08
    ç§Ģ
    -0.08
    aque
    -0.08
    phin
    -0.08
    æ´¼
    -0.08
    ibe
    -0.08
    POSITIVE LOGITS
    åŃĺéĩı
    0.11
    è¿Ļå¼ł
    0.10
    åIJĥè¿ĩ
    0.09
    éĽĦåİļ
    0.09
    ä¸¤å¼ł
    0.09
     garg
    0.09
    èĪĴ
    0.09
    ä¸Ī
    0.08
    åºľ
    0.08
    æ¸ħ
    0.08
    Activations Density 0.031%

    No Known Activations