© 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. 33887
    Prev
    Next
    INDEX
    Explanations

    stages and age

    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
    第ä¸ĢåĮ»éĻ¢
    -0.10
    ìį¨
    -0.10
    Leaks
    -0.08
    isson
    -0.08
    ุ
    -0.08
    ington
    -0.08
    schen
    -0.08
    ä¸Ńèįīèį¯
    -0.08
    eland
    -0.07
    á»ĩn
    -0.07
    POSITIVE LOGITS
    amento
    0.09
    ë³Ħ
    0.08
    ä¸įåīį
    0.08
    coach
    0.08
    ë³Ħë¡ľ
    0.08
    ROUP
    0.08
    ement
    0.08
     Petersburg
    0.07
    epend
    0.07
    ividual
    0.07
    Activations Density 0.024%

    No Known Activations