© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 55191
    Prev
    Next
    INDEX
    Explanations

    interactive commands and shells

    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
     Hayward
    -0.07
     mou
    -0.07
    abouts
    -0.07
    æIJľç´¢çĽ¸åħ³èµĦæĸĻ
    -0.07
    PropertyChanged
    -0.06
    åIJĦæľī
    -0.06
    è£ħ车
    -0.06
    ounty
    -0.06
    丰满
    -0.06
     morally
    -0.06
    POSITIVE LOGITS
    _commands
    0.09
     executing
    0.09
    èĦļæīĭ
    0.09
     Execute
    0.08
     commands
    0.08
    rompt
    0.08
    executor
    0.08
    Executor
    0.08
    ExecutionContext
    0.08
    Execute
    0.08
    Activations Density 0.253%

    No Known Activations