© 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. 42246
    Prev
    Next
    INDEX
    Explanations

    powered by energy or electrical

    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
    大èĥĨ
    -0.08
    åĽŀåºĶ
    -0.07
    æľīéĴĪ对æĢ§
    -0.07
    vars
    -0.07
    ç»Ĩ鼨
    -0.07
    .cv
    -0.07
    ofil
    -0.07
    _INCLUDE
    -0.07
    abyte
    -0.07
     Pitch
    -0.07
    POSITIVE LOGITS
    驱åĬ¨çļĦ
    0.10
    驱åĬ¨
    0.10
    缴æİ¥æĪĸéĹ´æİ¥
    0.10
     indirectly
    0.09
    -powered
    0.09
     powering
    0.08
    -driven
    0.08
    èĥ½éĩıçļĦ
    0.08
    æīĢæıIJä¾ĽçļĦ
    0.08
    çļĦèĥ½éĩı
    0.08
    Activations Density 0.112%

    No Known Activations