© 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. 13724
    Prev
    Next
    INDEX
    Explanations

    code strings and expected values

    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
    ezo
    -0.08
    اÙĭ
    -0.07
    cy
    -0.07
    cdn
    -0.07
    ĭ
    -0.07
    ezu
    -0.07
    upa
    -0.07
    psilon
    -0.06
    аÑİÑĤ
    -0.06
    æł·çļĦ
    -0.06
    POSITIVE LOGITS
    s
    0.12
    缸è¾ħ缸æĪIJ
    0.11
    åį³éĢĿ
    0.09
    åijIJ
    0.09
    vironment
    0.09
    ghi
    0.09
    র
    0.08
    äºĭåįĬåĬŁåĢį
    0.08
    sider
    0.08
    sä
    0.08
    Activations Density 0.018%

    No Known Activations