© 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. 40577
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and code syntax

    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
    ocache
    -0.12
    ewire
    -0.08
    .CreateCommand
    -0.08
    ÑħÑĸ
    -0.07
    enet
    -0.07
    InputChange
    -0.07
    obuf
    -0.07
    atil
    -0.07
    EDO
    -0.07
    aina
    -0.07
    POSITIVE LOGITS
     yield
    0.07
    ulare
    0.06
     bound
    0.06
     etc
    0.06
    欧
    0.06
    arius
    0.06
    ãģªãģ©ãģ®
    0.05
     super
    0.05
     ro
    0.05
    ãģı
    0.05
    Activations Density 0.008%

    No Known Activations