© 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. 50095
    Prev
    Next
    INDEX
    Explanations

    date and time formats

    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
    auer
    -0.07
    oure
    -0.07
    chaffen
    -0.07
    okban
    -0.06
    اد
    -0.06
    .TODO
    -0.06
    ä¸¤åľº
    -0.06
    )&&
    -0.06
    heck
    -0.06
    ÅĤa
    -0.06
    POSITIVE LOGITS
    ä¸ĭåIJĮ
    0.09
    rost
    0.07
     ATS
    0.07
    <|box_end|>
    0.07
    ä¸İåħ±
    0.07
    addock
    0.07
    åıĪä¸įæĺ¯
    0.07
    åıĪæĺ¯
    0.07
    åıĪä¸įèĥ½
    0.07
    _tpl
    0.07
    Activations Density 0.037%

    No Known Activations