© 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. 47655
    Prev
    Next
    INDEX
    Explanations

    replace instead

    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
    åŀĴ
    -0.08
    ppe
    -0.07
    ÂŃs
    -0.07
    bourg
    -0.07
    areth
    -0.07
    chenk
    -0.07
     geboren
    -0.07
    apol
    -0.07
    toff
    -0.07
     pesta
    -0.07
    POSITIVE LOGITS
    æļ®
    0.07
    裳
    0.07
    LOC
    0.07
    _tC
    0.06
    å¤ĦçIJĨæĸ¹æ³ķ
    0.06
    weise
    0.06
    ¬ģ
    0.06
    çĶŁæ°´
    0.06
    湿润
    0.06
    缼çļĦ
    0.06
    Activations Density 0.001%

    No Known Activations