© 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. 44905
    Prev
    Next
    INDEX
    Explanations

    URL parameters and actions

    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
    Ñĩе
    -0.07
    osz
    -0.06
    ว
    -0.06
     Ganz
    -0.06
    _perc
    -0.06
    .getOwnPropertyDescriptor
    -0.06
     Mac
    -0.06
    ropp
    -0.06
    åĶ
    -0.06
    ä¸Ģè¦ģ
    -0.06
    POSITIVE LOGITS
     dò
    0.07
    OfMonth
    0.07
    è´¨
    0.07
    OfDay
    0.07
    龧
    0.07
    avern
    0.07
    Hal
    0.06
    .dispatch
    0.06
    pozy
    0.06
    ,ll
    0.06
    Activations Density 0.019%

    No Known Activations