© 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. 32381
    Prev
    Next
    INDEX
    Explanations

    file extensions: .css, .py, .js

    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
    arn
    -0.07
    ono
    -0.07
     Pedi
    -0.06
    rowse
    -0.06
    agma
    -0.06
    ern
    -0.06
    imon
    -0.05
     misc
    -0.05
    uro
    -0.05
    ç½
    -0.05
    POSITIVE LOGITS
    avance
    0.08
    ãĤ¤ãĥĦ
    0.08
    ienz
    0.08
    平平å®ī
    0.08
    缸çľĭ
    0.08
    wez
    0.08
    ê¶ģ
    0.07
    пÑĭÑĤ
    0.07
    stub
    0.07
    лÑĸн
    0.07
    Activations Density 0.174%

    No Known Activations