© 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. 55416
    Prev
    Next
    INDEX
    Explanations

    confectionery, infection, mucus, router

    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
    izedName
    -0.09
    auern
    -0.09
    ãĤĦãģ¯
    -0.09
    aturi
    -0.09
    IZER
    -0.09
    yiz
    -0.09
    ริà¸ĩ
    -0.09
    кеÑĢ
    -0.08
    ableObject
    -0.08
    enderit
    -0.08
    POSITIVE LOGITS
    0.12
    ä¹İ
    0.11
    ฯ
    0.10
    o
    0.08
    us
    0.08
    âĢĮ
    0.07
    i
    0.07
    ute
    0.07
    ãĢħ
    0.07
    ú
    0.07
    Activations Density 5.623%

    No Known Activations