© 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. 41394
    Prev
    Next
    INDEX
    Explanations

    digital pins or numbers

    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
    è¯ī
    -0.06
     gắt
    -0.06
    訴
    -0.06
    èĨĬ
    -0.06
    èĻİ
    -0.06
    èį
    -0.06
    sker
    -0.06
    é
    -0.06
    åħ«åŃĹ
    -0.06
    Invoker
    -0.06
    POSITIVE LOGITS
    ç«Ļ
    0.08
    ugu
    0.08
    Gun
    0.08
     slags
    0.07
    artet
    0.07
    æĸ°æŃĮ
    0.07
    uali
    0.07
    å¤ªè¿ľ
    0.07
     Station
    0.07
    .same
    0.07
    Activations Density 0.187%

    No Known Activations