© 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. 16611
    Prev
    Next
    INDEX
    Explanations

    watch or watches preceding a descriptor or feature

    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
    emand
    -0.10
    饱满
    -0.10
    第ä¸Ģéĥ¨
    -0.09
    åij±
    -0.09
    æĶ¾çľ¼
    -0.09
    çĢĽ
    -0.09
    ridor
    -0.09
    vil
    -0.09
    ä»Ģä¹Īä¸ľè¥¿
    -0.09
    uan
    -0.09
    POSITIVE LOGITS
    maker
    0.13
    makers
    0.12
    gi
    0.10
    oret
    0.10
    ski
    0.09
    Ñĩик
    0.09
    keit
    0.09
    å¯IJ
    0.09
    èĥ¡
    0.09
    -maker
    0.09
    Activations Density 0.017%

    No Known Activations