© 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. 4313
    Prev
    Next
    INDEX
    Explanations

    formula

    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
    ools
    -0.07
    >').
    -0.07
    Runnable
    -0.06
    æīĢ欲è¨Ģ
    -0.06
    adoo
    -0.06
    ueb
    -0.06
    ume
    -0.06
     Hope
    -0.06
    åIJĴ
    -0.06
    essor
    -0.06
    POSITIVE LOGITS
    hie
    0.08
    )-(
    0.07
    vani
    0.07
    åľ£
    0.07
    ç¨ĭå¼ı
    0.07
    quetas
    0.07
    jeta
    0.06
     definitions
    0.06
    mula
    0.06
    ä¸Ģ大åłĨ
    0.06
    Activations Density 0.002%

    No Known Activations