© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 18571
    Prev
    Next
    INDEX
    Explanations

    Department of

    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
    rô
    -0.09
    ä»ĭ
    -0.09
    å¸Ī
    -0.09
    漪
    -0.09
    برا
    -0.09
    å°ıå¿ĥ
    -0.09
    çļĦèī¯å¥½
    -0.08
    Mot
    -0.08
     Mot
    -0.08
    åIJİæİĴ
    -0.08
    POSITIVE LOGITS
    åĬŀåħ¬åİħ
    0.10
    è´¢æĶ¿éĥ¨
    0.10
    ä»İæĿ¥æ²¡æľī
    0.10
    å°ļ书
    0.09
    æ¯ķç«Łæĺ¯
    0.09
    åĪł
    0.09
    etary
    0.09
     Homeland
    0.09
    istry
    0.09
    ÑĨиалÑĮно
    0.09
    Activations Density 0.092%

    No Known Activations