© 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. 50289
    Prev
    Next
    INDEX
    Explanations

    season, sales, production, productivity, height, rows, coordinates

    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
    çĶŁç´ł
    -0.08
    ابع
    -0.07
    fera
    -0.07
    asca
    -0.07
    otton
    -0.07
    olds
    -0.07
    ataires
    -0.07
    icoli
    -0.07
    JKLM
    -0.07
     Kla
    -0.07
    POSITIVE LOGITS
    亡
    0.09
    ä¸İçłĶ究
    0.07
    _opts
    0.07
    诱
    0.07
    çĤ¯
    0.07
    åºŃ
    0.06
     inf
    0.06
    ivil
    0.06
    ivan
    0.06
    اص
    0.06
    Activations Density 0.249%

    No Known Activations