© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62872
    Prev
    Next
    INDEX
    Explanations

    JavaScript code for events

    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
     boxed
    -0.06
    cesi
    -0.06
    erty
    -0.06
    onso
    -0.05
    iane
    -0.05
    oca
    -0.05
    ertes
    -0.05
    elaar
    -0.05
     appunto
    -0.05
    ovsky
    -0.05
    POSITIVE LOGITS
    å¾·æĻº
    0.08
    è¿Ľåı£çļĦ
    0.08
    êm
    0.07
    çħ§çĽ¸
    0.07
    wel
    0.07
    ifecycle
    0.07
    ”(
    0.07
    maf
    0.07
     <<-
    0.07
    websocket
    0.07
    Activations Density 0.052%

    No Known Activations