© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 8891
    Prev
    Next
    INDEX
    Explanations

    Google Cloud Service Account

    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
    å°±åľ¨è¿Ļ
    -0.08
    impa
    -0.08
    йо
    -0.08
    åºķä¸ĭ
    -0.07
    ä¸ĭåIJĮ
    -0.07
    对ä»ĸ们
    -0.07
    .fm
    -0.07
     aplik
    -0.07
    Indexed
    -0.07
     appName
    -0.07
    POSITIVE LOGITS
     âĢŀ
    0.06
    azon
    0.06
    ern
    0.06
    idth
    0.06
    æij¸æij¸
    0.06
    *:
    0.06
    Âł
    0.06
    ”:
    0.06
    **:
    0.06
    oret
    0.06
    Activations Density 0.008%

    No Known Activations