© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46695
    Prev
    Next
    INDEX
    Explanations

    clockwise, counterclockwise, CW, CCW

    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
     liá»ĩu
    -0.10
     Ñģобой
    -0.09
    гоÑĢа
    -0.08
    aint
    -0.08
    asten
    -0.08
    azer
    -0.08
    tle
    -0.07
    .setUp
    -0.07
    arb
    -0.07
    wig
    -0.07
    POSITIVE LOGITS
    icch
    0.07
    ly
    0.07
    /right
    0.07
    ról
    0.07
    uhan
    0.07
    -ish
    0.07
    íİ
    0.06
    lich
    0.06
    brew
    0.06
    åľı
    0.06
    Activations Density 0.002%

    No Known Activations