© 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. 14116
    Prev
    Next
    INDEX
    Explanations

    rate of return

    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
    cion
    -0.07
    ä¿Ŀéļľ
    -0.07
    aqu
    -0.07
    好æĸĩ
    -0.07
    aff
    -0.07
    lett
    -0.07
    ConnectionFactory
    -0.06
     blat
    -0.06
    -defense
    -0.06
    çĻ½å¤ľ
    -0.06
    POSITIVE LOGITS
    åıĪåı«
    0.08
    NDER
    0.08
    趾
    0.08
     Pereira
    0.08
    æĸĮ
    0.07
    满头
    0.07
     MBA
    0.07
     discounted
    0.07
    kho
    0.07
    ToDate
    0.07
    Activations Density 0.001%

    No Known Activations