© 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. 24938
    Prev
    Next
    INDEX
    Explanations

    EventId, personId, relationId

    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
    quip
    -0.07
     Gre
    -0.07
    ijt
    -0.07
    个èµŀ
    -0.07
    uus
    -0.07
    婪
    -0.07
    ..\
    -0.07
    /md
    -0.07
     Mittler
    -0.07
     dead
    -0.06
    POSITIVE LOGITS
    å°
    0.07
    åįļ
    0.07
    à¹Ħà¸Ļ
    0.07
    鸣
    0.07
     بب
    0.07
    adb
    0.07
    oden
    0.07
     Dawson
    0.07
    asper
    0.07
    åĽŀé¦ĸ
    0.06
    Activations Density 0.084%

    No Known Activations