© 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. 28558
    Prev
    Next
    INDEX
    Explanations

    std::macro

    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
    èĮ¬
    -0.07
    aw
    -0.06
    st
    -0.06
    ève
    -0.06
    é¡¹çĽ®æĢ»æĬķèµĦ
    -0.06
    å²Ľ
    -0.06
    -st
    -0.06
    èves
    -0.06
    رÙģ
    -0.06
     Matthews
    -0.06
    POSITIVE LOGITS
    xac
    0.07
     Tro
    0.07
    icama
    0.07
    å¼łå»º
    0.07
    ä¸ĢæŶ
    0.07
    iesa
    0.07
     наÑĢи
    0.07
    hlas
    0.07
    orti
    0.07
    ):-
    0.07
    Activations Density 0.054%

    No Known Activations