© 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. 33322
    Prev
    Next
    INDEX
    Explanations

    unity `&` `ID` tags

    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
    emme
    -0.07
    æľīéģĵ
    -0.07
    满æĢĢ
    -0.06
    kste
    -0.06
    ä¿¡ãģĺ
    -0.06
    è¯Ħä»·æĮĩæłĩ
    -0.06
    éĻĦåĬł
    -0.06
    rosa
    -0.06
    _servers
    -0.06
    italize
    -0.06
    POSITIVE LOGITS
    .blank
    0.08
    azan
    0.08
    olin
    0.07
    entak
    0.07
    _NULL
    0.07
    okies
    0.07
    å¿ħ究
    0.07
    ä¸įåĩĨ
    0.07
    دÙĨ
    0.07
    _MATCH
    0.07
    Activations Density 0.006%

    No Known Activations