© 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. 16376
    Prev
    Next
    INDEX
    Explanations

    revenue

    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
    ÑĤол
    -0.07
    æĪIJåIJį
    -0.06
    боÑİ
    -0.06
    ness
    -0.06
     nhau
    -0.06
    .getBoundingClientRect
    -0.06
    reet
    -0.06
    maz
    -0.06
    shore
    -0.06
    aroo
    -0.06
    POSITIVE LOGITS
    ources
    0.09
     revenue
    0.08
     vẹn
    0.08
    ÑĢÑĭз
    0.08
    ossos
    0.08
     Umsatz
    0.08
    çĤ¹çĤ¹æ»´æ»´
    0.08
    主è¦ģæĿ¥èĩª
    0.07
    odaw
    0.07
    æ·¡åŃ£
    0.07
    Activations Density 0.028%

    No Known Activations