© 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. 18067
    Prev
    Next
    INDEX
    Explanations

    operators and operands

    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
    é£İè¡Į
    -0.08
    urt
    -0.07
     Fires
    -0.07
    çĪ±å°Ķ
    -0.07
    plat
    -0.07
    جÙĬÙĦ
    -0.07
    lak
    -0.07
    erton
    -0.07
    ä¹ŁæĮº
    -0.07
    éĿ¢æĹł
    -0.07
    POSITIVE LOGITS
    amble
    0.07
    _COMPLEX
    0.07
    exual
    0.07
    áros
    0.07
    ÑģÑĤиÑĤе
    0.06
    ·¸
    0.06
    arani
    0.06
    _strip
    0.06
    缸äºĴ交æµģ
    0.06
    еÑģп
    0.06
    Activations Density 0.094%

    No Known Activations