© 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. 65421
    Prev
    Next
    INDEX
    Explanations

    content locking

    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
    avigate
    -0.08
    ä½ķçŃī
    -0.07
    è¿İéļ¾
    -0.07
    ours
    -0.07
    ãĤĮãģ°
    -0.07
    alani
    -0.07
    adero
    -0.06
    hta
    -0.06
    reich
    -0.06
    otty
    -0.06
    POSITIVE LOGITS
    -packages
    0.07
    enius
    0.06
    à¥Ĥस
    0.06
    lant
    0.06
    èĩªå·±
    0.06
    ód
    0.06
    neu
    0.06
    çİĭéģĵ
    0.06
    ses
    0.06
    rof
    0.06
    Activations Density 0.445%

    No Known Activations