© 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. 29482
    Prev
    Next
    INDEX
    Explanations

    four

    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
    atten
    -0.08
    两åij¨åĨħ
    -0.08
    -bin
    -0.08
    Bin
    -0.07
    ops
    -0.07
     Wagen
    -0.07
    è¿Ļ两ç§į
    -0.07
     Ten
    -0.07
    Ten
    -0.07
    åĩīäºĨ
    -0.07
    POSITIVE LOGITS
    åĽĽä¸ª
    0.20
    è¿ĻåĽĽä¸ª
    0.17
    åĽĽåĢĭ
    0.17
     four
    0.16
    four
    0.16
    åĽĽäºº
    0.16
    è¿ĻåĽĽ
    0.15
    åĽĽä¸ªäºº
    0.15
    åĽĽç§į
    0.14
     Four
    0.14
    Activations Density 0.177%

    No Known Activations