© 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. 64775
    Prev
    Next
    INDEX
    Explanations

    post follows, answer menu, measuring devices

    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
    imest
    -0.07
    lands
    -0.07
    خر
    -0.06
     Elaine
    -0.06
    ls
    -0.06
    els
    -0.06
    llen
    -0.06
    ãĤ´ãĥ¼
    -0.06
    _SCHEMA
    -0.06
    iché
    -0.06
    POSITIVE LOGITS
     milan
    0.08
    ertes
    0.07
    εÏģι
    0.07
    WithString
    0.07
    à¸Ńร
    0.07
    涵
    0.07
     übrigens
    0.07
    å°ı家
    0.07
    æĬ¤
    0.07
    dio
    0.07
    Activations Density 0.002%

    No Known Activations