© 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. 46360
    Prev
    Next
    INDEX
    Explanations

    numbers and measurements

    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
     cons
    -0.07
    ä¹Łä¸įè¿ĩ
    -0.07
    ears
    -0.07
    between
    -0.06
     interpol
    -0.06
    kers
    -0.06
    zien
    -0.06
     Mar
    -0.06
    brid
    -0.06
    را
    -0.06
    POSITIVE LOGITS
    ople
    0.09
    Grace
    0.08
    åIJįåī¯
    0.08
    DownList
    0.08
    inyin
    0.08
     lesser
    0.07
    OrElse
    0.07
    peater
    0.07
     bø
    0.07
    .Builder
    0.07
    Activations Density 0.137%

    No Known Activations