© 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. 2180
    Prev
    Next
    INDEX
    Explanations

    second derivative calculations

    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
    utura
    -0.07
    ä¸įåı¯ç¼ºå°ij
    -0.07
    綾
    -0.07
    iat
    -0.07
    verages
    -0.07
    è²¢
    -0.06
    .insertBefore
    -0.06
    aturi
    -0.06
    ixel
    -0.06
    pbs
    -0.06
    POSITIVE LOGITS
    ç½Ħ
    0.08
     Tut
    0.07
    itar
    0.07
     tut
    0.07
    );$
    0.07
    iple
    0.07
    åĪĿä¸Ģ
    0.07
    "]]
    0.07
    éĨĴæĿ¥
    0.07
    nev
    0.06
    Activations Density 0.008%

    No Known Activations