© 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. 64813
    Prev
    Next
    INDEX
    Explanations

    code scripts and simulation

    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
    _syntax
    -0.08
    acey
    -0.07
    armo
    -0.07
    çļ®çļĦ
    -0.07
    _strerror
    -0.07
    bies
    -0.07
     arithmetic
    -0.07
    .DataType
    -0.07
    豺
    -0.06
    ihal
    -0.06
    POSITIVE LOGITS
    模æĭŁ
    0.09
     simulate
    0.08
     simulated
    0.08
    èĻļæĭŁ
    0.08
     Actions
    0.07
    _allowed
    0.07
     simul
    0.07
     actions
    0.07
    Actions
    0.07
    simulate
    0.07
    Activations Density 0.014%

    No Known Activations