© 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. 58884
    Prev
    Next
    INDEX
    Explanations

    in this case

    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
    çħŀ
    -0.10
    è¿ĺåı¯
    -0.08
    åģĮ
    -0.08
    ä¿ĥæĪIJ
    -0.08
     Conn
    -0.08
    erner
    -0.08
    SEC
    -0.08
    éī´åĪ«
    -0.08
    softmax
    -0.08
    å¹²åĺĽ
    -0.08
    POSITIVE LOGITS
     case
    0.14
     caso
    0.14
    æĥħåĨµä¸ĭ
    0.13
    æľ¬æ¡Ī
    0.13
     ÑģлÑĥÑĩае
    0.13
     ×ij×ŀקר×Ķ
    0.12
    è¿Ļç§įæĥħåĨµ
    0.12
    ãģ®åł´åIJĪ
    0.12
     ÑģлÑĥÑĩаÑı
    0.12
    è¿ĻéĩĮæĺ¯
    0.12
    Activations Density 0.223%

    No Known Activations