© 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. 21961
    Prev
    Next
    INDEX
    Explanations

    file paths and directories like `Files`, `SOFTWARE`, `Library`

    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
    bruck
    -0.07
    eta
    -0.07
     fresh
    -0.07
     Sorg
    -0.06
    gé
    -0.06
    åľ¨ä¸Ģçīĩ
    -0.06
     pell
    -0.06
    æĸŃ
    -0.06
    åĿĹ
    -0.06
    μβα
    -0.06
    POSITIVE LOGITS
    orten
    0.07
    -contrib
    0.07
    _APPS
    0.07
    æĭ¡å¼µ
    0.07
    æ¨Ł
    0.07
    ืà¸Ńà¸ĩ
    0.07
    è¿Ľä¸ĢæŃ¥è§ĦèĮĥ
    0.06
    rats
    0.06
     Conexion
    0.06
    æıĴæīĭ
    0.06
    Activations Density 0.081%

    No Known Activations