© 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. 55857
    Prev
    Next
    INDEX
    Explanations

    Hundred Days

    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
    utsche
    -0.07
    icas
    -0.07
    alam
    -0.07
    казÑĭ
    -0.07
    uts
    -0.07
    交
    -0.07
    alia
    -0.07
    isiones
    -0.07
    ALAR
    -0.07
    豪
    -0.07
    POSITIVE LOGITS
     ctypes
    0.07
    )':
    0.07
    еÑĢа
    0.06
    Ñħло
    0.06
    ocu
    0.06
    çļĦ详ç»Ĩ
    0.06
    innerHTML
    0.06
     rebut
    0.06
    itez
    0.06
    åįĬæŃ¥
    0.06
    Activations Density 0.034%

    No Known Activations