© 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. 6039
    Prev
    Next
    INDEX
    Explanations

    Chief, Satellite, Friends, thesis

    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
    ä¸ĢåĪĨ
    -0.11
    arna
    -0.10
    acades
    -0.09
    riter
    -0.09
     Lor
    -0.09
    ɸ
    -0.09
    otti
    -0.09
    strup
    -0.09
    _BGR
    -0.08
    .xhtml
    -0.08
    POSITIVE LOGITS
    دب
    0.09
    åįĹè·¯
    0.08
    åīįèĢħ
    0.08
    åIJİå¤ĩ
    0.08
     بÙĪ
    0.08
    è¨Ĺ
    0.08
    家çĶ¨
    0.08
    纪
    0.08
    åIJİèĢħ
    0.08
    纳
    0.07
    Activations Density 0.428%

    No Known Activations