© 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. 24725
    Prev
    Next
    INDEX
    Explanations

    presence of probability statistics

    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
    izard
    -0.08
    elper
    -0.08
    inting
    -0.07
    ergus
    -0.07
    ä¸Ģ空
    -0.07
    artin
    -0.07
    ourd
    -0.07
    заÑĢ
    -0.07
    ublic
    -0.07
    ât
    -0.07
    POSITIVE LOGITS
    ä¸Ńæļij
    0.07
    ATAL
    0.06
    eps
    0.06
    è¡Ľ
    0.06
     st
    0.06
    EV
    0.06
    åıĹçIJĨ
    0.06
    ав
    0.06
    严éĩįè¿Ŀæ³ķ
    0.06
    null
    0.06
    Activations Density 0.434%

    No Known Activations