© 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. 43674
    Prev
    Next
    INDEX
    Explanations

    quad x and dx

    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
    иÑİ
    -0.08
    elow
    -0.08
    i
    -0.08
    ä¼ĹæīĢåij¨çŁ¥
    -0.08
    ات
    -0.08
    plier
    -0.08
    italia
    -0.08
    iad
    -0.07
    ierra
    -0.07
    ãģĦãĤĭ
    -0.07
    POSITIVE LOGITS
    vice
    0.07
    YNAMIC
    0.07
    isplay
    0.07
    ings
    0.07
    ently
    0.07
    ient
    0.07
    ìĦľëĬĶ
    0.07
    time
    0.06
    ף
    0.06
    nable
    0.06
    Activations Density 0.001%

    No Known Activations