© 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. 18836
    Prev
    Next
    INDEX
    Explanations

    variable declaration and assignment

    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
    !--
    -0.09
    ilder
    -0.08
    йм
    -0.08
    áĢĬáĢºáĢ¸
    -0.08
    NSS
    -0.07
    <!--[
    -0.07
    CONDITION
    -0.07
    öll
    -0.07
    åĮ¿åIJįçĶ¨æĪ·
    -0.07
    amework
    -0.07
    POSITIVE LOGITS
    exit
    0.07
     exit
    0.06
    aat
    0.06
    IMIT
    0.06
    oso
    0.06
    osat
    0.06
    欢
    0.06
    ikten
    0.06
    åı¯åĸľ
    0.06
     exits
    0.06
    Activations Density 0.015%

    No Known Activations