© 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. 28488
    Prev
    Next
    INDEX
    Explanations

    main, repository, scripts keywords

    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
     دک
    -0.08
     desto
    -0.08
    vert
    -0.08
    verty
    -0.07
    å¸ĥ鼷
    -0.07
    cca
    -0.07
    wann
    -0.07
     libertine
    -0.07
    logen
    -0.07
    èĩªæĿ¥æ°´
    -0.07
    POSITIVE LOGITS
    undi
    0.07
    _:
    0.07
    çķĻä¸ĭæĿ¥çļĦ
    0.06
    endor
    0.06
    endors
    0.06
    istes
    0.06
    nota
    0.06
    ÑĢов
    0.06
    exception
    0.06
    back
    0.06
    Activations Density 0.001%

    No Known Activations