© 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. 2477
    Prev
    Next
    INDEX
    Explanations

    kinematics

    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
    igny
    -0.08
    รวà¸ĩ
    -0.07
    iente
    -0.07
    indle
    -0.07
    ©
    -0.07
    iveness
    -0.06
    iates
    -0.06
    ivant
    -0.06
    zinho
    -0.06
    ä¹ĭè¡Į
    -0.06
    POSITIVE LOGITS
    etic
    0.10
    arki
    0.08
    ally
    0.08
    ascus
    0.08
    /environment
    0.08
    ALLY
    0.08
    erals
    0.08
    ä¸ĢåĬ¨
    0.08
    ematic
    0.08
    raż
    0.08
    Activations Density 0.005%

    No Known Activations