© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 64055
    Prev
    Next
    INDEX
    Explanations

    45 degrees

    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
    诺è¨Ģ
    -0.07
    ivent
    -0.07
    oso
    -0.07
    ела
    -0.07
    æĸĩç§ij
    -0.07
    컬
    -0.07
    omo
    -0.06
    aczy
    -0.06
    ekat
    -0.06
    änen
    -0.06
    POSITIVE LOGITS
    ÑĦей
    0.07
    agram
    0.07
    erder
    0.07
    ube
    0.07
    ypress
    0.07
    à¸ļà¸Ķี
    0.07
    éĽĢ
    0.07
    elsius
    0.07
    çħ¦
    0.07
    TON
    0.06
    Activations Density 0.002%

    No Known Activations