© 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. 45852
    Prev
    Next
    INDEX
    Explanations

    xml/html tags

    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
    çİĭçİī
    -0.07
    ede
    -0.06
    isle
    -0.06
    å®ļçļĦ
    -0.06
    åĿIJçĿĢ
    -0.06
    tores
    -0.06
    -
    -0.06
    trom
    -0.06
    rim
    -0.06
    å¥ĭè¿Ľ
    -0.06
    POSITIVE LOGITS
    çª
    0.08
    riad
    0.08
    unload
    0.08
    ulia
    0.07
    ilai
    0.07
    rk
    0.07
    ulai
    0.07
    мна
    0.07
    araf
    0.07
    ETTA
    0.07
    Activations Density 0.001%

    No Known Activations