© 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. 24888
    Prev
    Next
    INDEX
    Explanations

    HTML component 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
    s
    -0.07
    ards
    -0.06
    ?,
    -0.06
    ARD
    -0.06
    (s
    -0.06
    举
    -0.06
    æİ¥çĿĢ
    -0.06
    .,
    -0.06
    >'.
    -0.06
    \
    -0.06
    POSITIVE LOGITS
    ä¾ĥ
    0.08
    MethodImpl
    0.08
    "value
    0.07
    ä¸İæĸĩåĮĸ
    0.07
    _APB
    0.07
    htable
    0.07
    ä¸İæľ¬ç«Ļ
    0.07
    cesa
    0.07
    æ¯Ķçħ§
    0.07
    PROC
    0.07
    Activations Density 0.117%

    No Known Activations