© 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. 60257
    Prev
    Next
    INDEX
    Explanations

    mathematical and physics concepts

    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
    remos
    -0.08
    loge
    -0.08
    ouser
    -0.08
    æľīä»·åĢ¼çļĦ
    -0.07
    urin
    -0.07
    /respond
    -0.07
    ån
    -0.07
    çĽ
    -0.07
    线索æķ°éĩı
    -0.07
    urant
    -0.07
    POSITIVE LOGITS
    çīĪçļĦ
    0.09
    éĻħ
    0.09
    çīĪ
    0.09
    -based
    0.08
     notation
    0.08
     version
    0.07
    æ³ķ
    0.07
    å±ĤéĿ¢
    0.07
    å±ĤéĿ¢çļĦ
    0.07
     VERSION
    0.07
    Activations Density 0.021%

    No Known Activations