© 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. 45719
    Prev
    Next
    INDEX
    Explanations

    SVG path data coordinates

    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
    wege
    -0.07
    neur
    -0.07
    гово
    -0.07
    ctor
    -0.07
    ecto
    -0.07
    ве
    -0.07
    arczy
    -0.06
    ÙĨØ©
    -0.06
    ä»Ĭå¤ľ
    -0.06
    érico
    -0.06
    POSITIVE LOGITS
    еÑĤÑĢо
    0.07
    ä¸ĭè°ĥ
    0.07
    åIJijä¸ĭ
    0.07
    íĦ°ë¦¬
    0.07
    åĪ©æ°ij
    0.07
    ç§ĭæľĪ
    0.07
    emperature
    0.07
    è¿Ľè¡ĮæIJľç´¢
    0.06
    åłĤçļĩ
    0.06
    ียว
    0.06
    Activations Density 0.044%

    No Known Activations