© 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. 26377
    Prev
    Next
    INDEX
    Explanations

    bubbling liquid surface

    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
    ä¹ī
    -0.09
    ä¿¡ä»°
    -0.09
    éĵ¢
    -0.09
    é¥®é£Ł
    -0.08
     Hust
    -0.08
    æīģ
    -0.08
    å¿įåıĹ
    -0.08
    å®ĺ
    -0.08
    VA
    -0.08
    uru
    -0.08
    POSITIVE LOGITS
    æ°´éĿ¢
    0.12
    漪
    0.11
    表éĿ¢
    0.11
    浪
    0.11
     Surface
    0.11
     surface
    0.10
    åij¼
    0.10
    åĶ¿
    0.10
    .surface
    0.10
    å¹³éĿĻ
    0.10
    Activations Density 0.056%

    No Known Activations