© 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. 16747
    Prev
    Next
    INDEX
    Explanations

    those or one

    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
    èĪģ
    -0.11
    å°ı女åŃ©
    -0.09
    å°ıå§ijå¨ĺ
    -0.09
    å§IJ妹
    -0.09
    çķĮçļĦ
    -0.09
    ä¸ĢåĪĩéĥ½æĺ¯
    -0.09
    ç»¿åľ°
    -0.09
    åį´æĺ¯
    -0.09
    å¡ŀå°Ķ
    -0.09
    ä¸ĢåĪĩéĥ½
    -0.09
    POSITIVE LOGITS
    ä¼łåĩº
    0.10
     fallout
    0.09
    ylene
    0.08
    æıĸ
    0.08
    åIJ«ä¹ī
    0.08
     Lancaster
    0.08
     Wizards
    0.08
    _blocking
    0.08
     Petty
    0.08
    åĭ¤
    0.08
    Activations Density 0.045%

    No Known Activations