© 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. 26489
    Prev
    Next
    INDEX
    Explanations

    technical terms and code fragments

    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
    ัà¸į
    -0.07
    ilo
    -0.07
    TTY
    -0.07
    ç§ijæĬĢèĤ¡ä»½æľīéĻIJåħ¬åı¸
    -0.06
    performance
    -0.06
    OTO
    -0.06
    大ä¸ĸçķĮ
    -0.06
    ίÏĥ
    -0.06
    pin
    -0.06
     Neb
    -0.06
    POSITIVE LOGITS
    esai
    0.07
    å¾ĭå·±
    0.07
    ienda
    0.07
    -wrap
    0.07
    estet
    0.07
    czyk
    0.07
    zial
    0.07
    dá
    0.07
    èĤĿ
    0.07
    å°ĶåŁº
    0.07
    Activations Density 0.008%

    No Known Activations