© 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. 40754
    Prev
    Next
    INDEX
    Explanations

    permanganate

    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
    åŁĭæĢ¨
    -0.07
    缸æĢĿ
    -0.06
    ownload
    -0.06
    isi
    -0.06
    inat
    -0.06
    åĢ©
    -0.06
    tered
    -0.06
    uilt
    -0.06
    é¤
    -0.06
    è¼Ķ
    -0.06
    POSITIVE LOGITS
    éħ¸éĴ¾
    0.09
    红衣
    0.07
    ä¸Ģç«Ļ
    0.07
    adou
    0.07
     abolition
    0.07
    indicator
    0.07
    avored
    0.07
     stain
    0.07
    upos
    0.07
     anus
    0.07
    Activations Density 0.003%

    No Known Activations