© 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. 49753
    Prev
    Next
    INDEX
    Explanations

    context

    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
    è¿ĽéĢĢ
    -0.07
    /proto
    -0.07
    é¦Ĩ
    -0.07
    æĢİä¹ĪåĬŀåij¢
    -0.07
    .valueOf
    -0.07
    brace
    -0.07
    .hasOwnProperty
    -0.07
    IMAL
    -0.07
    éįĭ
    -0.06
     hitt
    -0.06
    POSITIVE LOGITS
     context
    0.10
    idente
    0.08
    HandlerContext
    0.08
    .context
    0.08
    context
    0.08
    çĴĢ
    0.08
    Context
    0.08
    ctx
    0.07
     Context
    0.07
     contexts
    0.07
    Activations Density 0.178%

    No Known Activations