© 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. 40620
    Prev
    Next
    INDEX
    Explanations

    special characters and code

    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
    ÅĤon
    -0.06
    åĽŀ头
    -0.06
    plet
    -0.06
    TING
    -0.06
    åĨĻåŃĹ
    -0.06
    åĬŀåħ¬å®¤éĩĮ
    -0.06
    åľ°ä¸ĬçļĦ
    -0.06
     Hood
    -0.06
     excess
    -0.06
    uel
    -0.06
    POSITIVE LOGITS
    urga
    0.08
    allis
    0.08
    裡
    0.08
    yka
    0.07
    æĻ®éĢļ
    0.07
    以æĿ¥çļĦ
    0.07
    allas
    0.07
    ugs
    0.07
    ়
    0.07
    .getElement
    0.07
    Activations Density 0.001%

    No Known Activations