© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 11053
    Prev
    Next
    INDEX
    Explanations

    code file paths

    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
    ItemAt
    -0.07
    åħ³èĬĤ
    -0.07
    tel
    -0.07
    缮
    -0.07
    ue
    -0.07
    te
    -0.06
    ×Ŀ
    -0.06
    odo
    -0.06
    _invoke
    -0.06
    æĮģãģ¡
    -0.06
    POSITIVE LOGITS
    setMessage
    0.07
    odle
    0.07
    人åĽŀå¤į
    0.07
    ìĦł
    0.07
    ä¹ĭåħī
    0.07
    aglia
    0.07
    adel
    0.07
    гази
    0.07
    agin
    0.07
    iguez
    0.07
    Activations Density 0.158%

    No Known Activations