© 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. 29497
    Prev
    Next
    INDEX
    Explanations

    flexible inner containers

    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
    .gc
    -0.10
    两æīĭ
    -0.09
    ForObject
    -0.09
    rame
    -0.09
    _splits
    -0.09
    ä¸į幸
    -0.09
     Phill
    -0.09
    ä»ĸèĩªå·±
    -0.09
    .Fatalf
    -0.09
    å§ĵåIJį
    -0.09
    POSITIVE LOGITS
    èĭ¥æľī
    0.10
    祯
    0.09
    羡
    0.09
    ä¿Ĺ
    0.09
    ä¸į说
    0.09
    å¯Ĥ
    0.08
    骢
    0.08
     cul
    0.08
    å¤ĸåľ°
    0.08
    篷
    0.08
    Activations Density 0.048%

    No Known Activations