© 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. 47483
    Prev
    Next
    INDEX
    Explanations

    `Bar`, `color2`, `green`, `b`

    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
    åĿı
    -0.06
    计éĩı
    -0.06
    stral
    -0.06
    rant
    -0.06
    ebt
    -0.06
    åıĪæĬĬ
    -0.05
    Ĵ
    -0.05
    -
    -0.05
    ynn
    -0.05
    并ä¸Ķ
    -0.05
    POSITIVE LOGITS
    DEX
    0.09
    åIJĮçIJĨ
    0.09
     simila
    0.08
    çİĩåĴĮ
    0.08
    åѦçĶŁåĴĮ
    0.08
    piler
    0.08
    åįİå¾·
    0.08
    ancier
    0.08
    ored
    0.08
    ä¹Łç½¢
    0.07
    Activations Density 0.022%

    No Known Activations