© 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. 64841
    Prev
    Next
    INDEX
    Explanations

    measurement units

    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
    èĨ
    -0.06
    çĭł
    -0.06
    åѦåİĨ
    -0.05
    æıĸ
    -0.05
    å°ıæıIJ示
    -0.05
    ogi
    -0.05
    رج
    -0.05
    AccessException
    -0.05
    åIJĪåIJĮ约å®ļçļĦ
    -0.05
    u
    -0.05
    POSITIVE LOGITS
    ì§ľ
    0.11
    allon
    0.09
    åıĬ以ä¸ĬçļĦ
    0.09
    大å°ıçļĦ
    0.09
    [url
    0.08
    çļ®ä¹¦
    0.08
    åıĬ以ä¸ĭ
    0.08
    볼
    0.08
    panse
    0.08
    ernals
    0.08
    Activations Density 0.203%

    No Known Activations