© 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. 50359
    Prev
    Next
    INDEX
    Explanations

    enum values

    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
    portes
    -0.09
    .owl
    -0.07
    Sin
    -0.06
    aines
    -0.06
    æĺ¯æľ¬
    -0.06
    ond
    -0.06
    öp
    -0.06
    id
    -0.06
     esc
    -0.06
     Warren
    -0.06
    POSITIVE LOGITS
     sheer
    0.08
    以赴
    0.07
    :param
    0.07
    नà¥įदà¥įर
    0.07
     ì¹ĺ
    0.07
    blad
    0.07
    ç½Ħ
    0.07
    æĸ°æľº
    0.07
     trán
    0.07
    _COMPLEX
    0.07
    Activations Density 0.030%

    No Known Activations