© 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. 39054
    Prev
    Next
    INDEX
    Explanations

    accented character sequences

    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
    两èĢħ
    -0.09
     ëijIJ
    -0.09
    è¿Ļ两
    -0.09
     beiden
    -0.09
    è¿Ļ两ç§į
    -0.08
    è¿Ļ两个
    -0.08
     both
    -0.08
    à¸Ĺัà¹īà¸ĩสà¸Ńà¸ĩ
    -0.08
    两éĥ¨åĪĨ
    -0.08
     Both
    -0.08
    POSITIVE LOGITS
    ?,?,?,?,
    0.14
    ãĢģ
    0.13
    ãĢģãĢģãĢģ
    0.12
     ãĢģ
    0.11
    ãĢģãĢģ
    0.11
    äºĶ个
    0.11
    åħŃ个
    0.10
    äºĶç§į
    0.10
    åĽĽä¸ª
    0.10
    æĺ¥å¤ıç§ĭåĨ¬
    0.10
    Activations Density 0.077%

    No Known Activations