© 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. 28204
    Prev
    Next
    INDEX
    Explanations

    underlying causes, mechanisms, assumptions

    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
    adu
    -0.10
    ifiable
    -0.09
    ä¸Ĭåı£
    -0.09
    tingham
    -0.09
    olley
    -0.08
    Äĩu
    -0.08
    illot
    -0.08
    /english
    -0.08
    ero
    -0.08
    å¤ĸè§Ģ
    -0.08
    POSITIVE LOGITS
    most
    0.10
    neath
    0.09
    hood
    0.07
     tảng
    0.07
     olev
    0.07
    ings
    0.07
    /down
    0.07
    acent
    0.07
     ê¹Ķ
    0.06
    stry
    0.06
    Activations Density 0.014%

    No Known Activations