© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 9102
    Prev
    Next
    INDEX
    Explanations

    sports television

    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
    ä¸ĩåįĥçĵ¦
    -0.07
    WithPath
    -0.06
    SharedPtr
    -0.06
    ä¾ĥ
    -0.06
    iam
    -0.06
    æĬŀ
    -0.06
    igon
    -0.06
    ç©İ
    -0.06
     vik
    -0.06
    .TryParse
    -0.06
    POSITIVE LOGITS
    arez
    0.08
    åĪļæīį
    0.07
     cuz
    0.07
    \\\\
    0.07
     VARIABLE
    0.07
    azza
    0.07
    ermann
    0.07
    ubber
    0.07
    çİī溪
    0.07
    osz
    0.07
    Activations Density 0.092%

    No Known Activations