© 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. 39004
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming questions

    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
    ì²ĺ
    -0.07
    esame
    -0.07
    arez
    -0.06
     vs
    -0.06
    wk
    -0.06
    á»Ķ
    -0.06
    ok
    -0.06
    åıĸ
    -0.06
     suit
    -0.06
    顧
    -0.06
    POSITIVE LOGITS
    ashi
    0.08
    请æĮī
    0.07
    äºİè¡Į
    0.07
    onha
    0.07
    ä¸įèĥľ
    0.07
    eppe
    0.07
    LatLng
    0.06
    鹤
    0.06
    emu
    0.06
    请çĶ¨
    0.06
    Activations Density 0.157%

    No Known Activations