© 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. 47859
    Prev
    Next
    INDEX
    Explanations

    reverse, right, bottom, DESC

    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
    ame
    -0.07
    åIJİç»Ń
    -0.06
     forward
    -0.06
     morning
    -0.06
    åīįåı°
    -0.06
    èĢģäºĨ
    -0.06
    Morning
    -0.06
    roma
    -0.06
    æĹ©æĻ¨
    -0.06
    _PREFIX
    -0.06
    POSITIVE LOGITS
    åĽŀçļĦ
    0.08
     rück
    0.08
    pper
    0.08
     rút
    0.08
    åĽŀæĴ¤
    0.08
    WARDS
    0.08
     обÑĢаÑĤ
    0.08
    åĢĴæķ°
    0.08
    éĢĨè¡Į
    0.08
    hend
    0.08
    Activations Density 0.013%

    No Known Activations