© 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. 62531
    Prev
    Next
    INDEX
    Explanations

    block structure

    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
     khúc
    -0.09
    ä¸įåĨ³
    -0.09
    รà¹īาย
    -0.09
    lande
    -0.09
    gnore
    -0.09
    Ù°
    -0.08
    iglio
    -0.08
    astas
    -0.08
    inten
    -0.08
    æīĢæľª
    -0.08
    POSITIVE LOGITS
    buster
    0.09
    ruptcy
    0.09
    ingly
    0.08
    busters
    0.08
    wise
    0.08
    SIZE
    0.08
    tober
    0.08
    iewicz
    0.08
    wagon
    0.07
    ness
    0.07
    Activations Density 0.030%

    No Known Activations