© 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. 13779
    Prev
    Next
    INDEX
    Explanations

    expected value or average

    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
     sebe
    -0.08
    élite
    -0.08
    ysl
    -0.07
     Salvini
    -0.07
    Mailer
    -0.07
    plit
    -0.07
    gangs
    -0.07
     Giud
    -0.07
    idah
    -0.07
     gara
    -0.07
    POSITIVE LOGITS
    çļĦå¹³åĿĩ
    0.10
     expectancy
    0.08
     average
    0.08
     Mean
    0.08
     Tav
    0.08
    å¹³åĿĩ
    0.08
     Average
    0.08
    æľŁæľĽ
    0.08
    åĬłæĿĥ
    0.08
    mean
    0.08
    Activations Density 0.011%

    No Known Activations