© 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. 20913
    Prev
    Next
    INDEX
    Explanations

    ï¬ģve stages

    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
    ionalmente
    -0.08
    aruhi
    -0.08
    inales
    -0.08
    apolis
    -0.08
    REFERRED
    -0.08
    ../../../../
    -0.07
    \/\/
    -0.07
    ularity
    -0.07
    foreign
    -0.07
    ously
    -0.07
    POSITIVE LOGITS
    ly
    0.10
    er
    0.09
    ing
    0.08
    able
    0.08
    ÛĮ
    0.07
    çĿĢ
    0.07
    ï¸ı
    0.07
    éĶµ
    0.07
    icker
    0.07
    tier
    0.07
    Activations Density 0.016%

    No Known Activations