© 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. 4015
    Prev
    Next
    INDEX
    Explanations

    ring theory, modules, categories

    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
    _running
    -0.07
    æ¦Ħ
    -0.07
     Hor
    -0.07
    NS
    -0.07
     extrapol
    -0.07
    обе
    -0.06
    olah
    -0.06
    è¿ŀè´¯
    -0.06
     Hover
    -0.06
    Hover
    -0.06
    POSITIVE LOGITS
    /Peak
    0.08
    åħ«éĥ¨
    0.08
    leet
    0.08
    ingleton
    0.08
    çłº
    0.08
    éĺ»åĩ»
    0.08
    FileNotFoundException
    0.07
    huizen
    0.07
     vÃłnh
    0.07
    Notifier
    0.07
    Activations Density 0.006%

    No Known Activations