© 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. 20098
    Prev
    Next
    INDEX
    Explanations

    comment markers

    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
    ?.
    -0.06
    纬
    -0.06
    èĢĮå·²
    -0.06
    اغ
    -0.06
     Maker
    -0.06
    x
    -0.06
    çªĥ
    -0.06
    uca
    -0.06
    并ç»ı
    -0.06
     bắp
    -0.06
    POSITIVE LOGITS
    ehme
    0.09
    ëŀĺ
    0.08
    ohan
    0.08
    LastError
    0.08
    alom
    0.08
    ctors
    0.08
    consts
    0.08
    neh
    0.08
    á»ı
    0.08
    åĸľæĢĴåĵĢ
    0.07
    Activations Density 0.006%

    No Known Activations