© 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. 24529
    Prev
    Next
    INDEX
    Explanations

    code syntax, programming, coding constructs

    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
    éªĨ
    -0.07
    umer
    -0.07
    koch
    -0.07
    å¾Īå¤ļåľ°æĸ¹
    -0.06
    akang
    -0.06
    anmar
    -0.06
    agher
    -0.06
     dug
    -0.06
     Ø£Ùĩ
    -0.06
    haps
    -0.06
    POSITIVE LOGITS
    راج
    0.09
    Explicit
    0.07
    å°Ĭ
    0.07
     kiá»ĩn
    0.07
    alli
    0.07
    顺åºı
    0.07
     Shotgun
    0.07
    kev
    0.07
    为å¸Ī
    0.07
     practise
    0.07
    Activations Density 0.001%

    No Known Activations