© 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. 57257
    Prev
    Next
    INDEX
    Explanations

    path representing

    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
    orium
    -0.07
    ä¸Ĭæ¦ľ
    -0.07
    oria
    -0.07
     (âĢ¦)
    -0.07
    åģ¿
    -0.07
    ApiClient
    -0.07
    reiz
    -0.07
    apore
    -0.07
    apon
    -0.06
    encial
    -0.06
    POSITIVE LOGITS
    å·²ä¹ħçļĦ
    0.07
    æĪ·æĻĵ
    0.07
     Hold
    0.07
     olev
    0.07
    âĹĩâĹĨ
    0.07
    ims
    0.07
    å¾·åŁº
    0.06
    ãģª
    0.06
    ixel
    0.06
    icable
    0.06
    Activations Density 0.152%

    No Known Activations