© 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. 31946
    Prev
    Next
    INDEX
    Explanations

    signs of measurement variability

    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
    以åıĬåľ¨
    -0.07
    以åıĬä¸ĢäºĽ
    -0.07
    éĻĨ
    -0.06
     ìŀIJ리를
    -0.06
    å¦ĩç§ijçĸ¾çĹħ
    -0.06
     gaz
    -0.06
    _DIRECTORY
    -0.06
    =>$
    -0.06
    å±ĭ
    -0.06
     ÙĤب
    -0.06
    POSITIVE LOGITS
    attan
    0.08
    μαÏĦο
    0.08
    èIJ½èĬ±
    0.08
    ä¸įå®ĮçļĦ
    0.07
    пÑĢиÑı
    0.07
    emui
    0.07
    ksam
    0.07
    اÙĦÛĮ
    0.07
    ankan
    0.07
    kaar
    0.07
    Activations Density 0.072%

    No Known Activations