© 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. 3732
    Prev
    Next
    INDEX
    Explanations

    key value pairs enclosed in curly braces

    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
    ä½ľ
    -0.07
    åı«ä»Ģä¹Ī
    -0.07
    ação
    -0.06
    驾驶
    -0.06
    ustin
    -0.06
    åħ¥åı£
    -0.06
    uffers
    -0.06
     ASSERT
    -0.06
    ä¸įåĩº
    -0.06
     ìĹ°
    -0.06
    POSITIVE LOGITS
    agno
    0.08
     perd
    0.08
    ibera
    0.07
    ÑĢÑĭм
    0.07
    orney
    0.07
    steder
    0.07
     equip
    0.07
    anser
    0.07
    anski
    0.07
    &M
    0.07
    Activations Density 0.001%

    No Known Activations