© 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. 48428
    Prev
    Next
    INDEX
    Explanations

    court, LED, or names

    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
    Ø©
    -0.09
    <|box_end|>
    -0.09
    ness
    -0.09
    ource
    -0.07
    à¹Į
    -0.07
    鼰
    -0.07
    ÄĽr
    -0.07
    åij³
    -0.07
    bye
    -0.06
    shire
    -0.06
    POSITIVE LOGITS
    ewe
    0.07
    对记èĢħ
    0.07
    ç¢Į
    0.07
    oleon
    0.07
    icy
    0.06
    deka
    0.06
    ucz
    0.06
    ãģ®ä¸Ńãģ§ãģ¯
    0.06
    abat
    0.06
    entic
    0.06
    Activations Density 0.029%

    No Known Activations