© 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. 56529
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    ķĮ
    -0.08
     Schuld
    -0.07
    usa
    -0.07
    каÑģ
    -0.06
    æ°´èįī
    -0.06
    kers
    -0.06
    åıĬè¦ģæ±Ĥ
    -0.06
    綴
    -0.06
    ä¹łæĢ»ä¹¦è®°
    -0.06
    eiros
    -0.06
    POSITIVE LOGITS
    plr
    0.07
    _macros
    0.07
    ÙĦاب
    0.07
    åŃļ
    0.07
    zil
    0.07
    ioc
    0.07
    ä¿¡
    0.07
    à¸Ľà¸£à¸±à¸ļà¸Ńาà¸ģาศ
    0.06
    ãģ¨ãĤĤãģ«
    0.06
    ç½ķ
    0.06
    Activations Density 0.029%

    No Known Activations