© 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. 25944
    Prev
    Next
    INDEX
    Explanations

    code compilation

    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
     finance
    -0.07
    AGMA
    -0.07
    åĴĮéĩįçĤ¹
    -0.07
    æĭ¬
    -0.07
    ÑĢаÑĤи
    -0.07
    atat
    -0.07
    adal
    -0.07
    ocate
    -0.07
    alisti
    -0.06
    (mesh
    -0.06
    POSITIVE LOGITS
     underlying
    0.09
    å®ĺæĸ¹
    0.09
    -based
    0.08
    ãģŀ
    0.08
    -Based
    0.07
     proprietary
    0.07
    æĮīçħ§è§Ħå®ļ
    0.07
    åİŁåİĤ
    0.07
    éļ
    0.07
     embodied
    0.07
    Activations Density 0.814%

    No Known Activations