© 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. 33883
    Prev
    Next
    INDEX
    Explanations

    U.S. Open Golf Championship, Rothmans International Tennis, F.3d 691

    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
    maÃŁen
    -0.10
    Åijl
    -0.10
    colar
    -0.09
    мин
    -0.09
    lern
    -0.09
    ered
    -0.08
    ationToken
    -0.08
    âĢ¦]
    -0.08
    zelf
    -0.08
    ãĥ£ãĥ³
    -0.08
    POSITIVE LOGITS
    ption
    0.12
    bject
    0.11
    gether
    0.11
    xffff
    0.10
    ä½Ļ个
    0.10
    ptions
    0.09
    portun
    0.09
    ehme
    0.08
    ceans
    0.08
    'Brien
    0.08
    Activations Density 1.183%

    No Known Activations