© 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. 4008
    Prev
    Next
    INDEX
    Explanations

    pen names, writing tools

    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
    heits
    -0.09
    åĿĢ
    -0.09
    ../../../
    -0.08
    zinho
    -0.08
     Ponti
    -0.07
    -0.07
    enticate
    -0.07
     Ganze
    -0.07
    ä¸įåıĬå¾ħ
    -0.07
     vá»įng
    -0.07
    POSITIVE LOGITS
    ä¸ĢæĮ¥
    0.10
    osity
    0.09
    mith
    0.08
    writing
    0.08
    åĮł
    0.07
    pen
    0.07
    wise
    0.07
     tangan
    0.07
    stroke
    0.07
    reira
    0.07
    Activations Density 0.058%

    No Known Activations