© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 43692
    Prev
    Next
    INDEX
    Explanations

    sum of different

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æł¹æľ¬å°±æĺ¯
    -0.08
     overall
    -0.07
    ÃŃn
    -0.07
    ίδα
    -0.07
    ä¸įèĭŁ
    -0.07
    å¿ĥæľī
    -0.07
    estone
    -0.07
    ä»»ä½ķäºĭæĥħ
    -0.06
    æĿ¥æºIJç½ij绾
    -0.06
    expanded
    -0.06
    POSITIVE LOGITS
    ":[{"
    0.08
    ä¸Ģ个个
    0.08
    à¹Ĩ
    0.08
    ноÑģÑĤей
    0.07
    fér
    0.07
     two
    0.06
    两éĥ¨åĪĨ
    0.06
    actions
    0.06
    å°¸
    0.06
    à¸Ńะà¹Ħรà¸ļà¹īาà¸ĩ
    0.06
    Activations Density 0.022%

    No Known Activations