© 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. 10351
    Prev
    Next
    INDEX
    Explanations

    code keywords and structure

    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
    illas
    -0.08
     rés
    -0.06
    actory
    -0.06
    ness
    -0.06
     FH
    -0.06
    ุà¸Ķ
    -0.06
    æĻ¶æĻ¶
    -0.06
    娴
    -0.06
    führende
    -0.06
    illo
    -0.06
    POSITIVE LOGITS
    ExceptionHandler
    0.08
    schutz
    0.07
    ppo
    0.07
    约èĢĮåIJĮ
    0.07
    Adr
    0.07
    incer
    0.07
    _WARNINGS
    0.07
    å©¿
    0.07
    yant
    0.07
    nger
    0.07
    Activations Density 0.026%

    No Known Activations