© 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. 13203
    Prev
    Next
    INDEX
    Explanations

    another followed by noun

    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
    ़
    -0.10
    ElementsBy
    -0.09
    agli
    -0.09
    ity
    -0.08
    åIJİè¿Ľ
    -0.08
    -0.08
    éĿ¡
    -0.08
    à¸Ĺัà¹īà¸ĩหลาย
    -0.08
    leston
    -0.08
    eil
    -0.07
    POSITIVE LOGITS
    er
    0.13
    æĪĸå¤ļ个
    0.12
    ly
    0.10
    åĴĮ
    0.10
    Ùĩ
    0.09
    æĪĸå¤ļ
    0.09
    ë¡ľ
    0.09
    erk
    0.09
    o
    0.09
    ой
    0.09
    Activations Density 0.028%

    No Known Activations