© 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. 30474
    Prev
    Next
    INDEX
    Explanations

    code structure indicators

    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
    績
    -0.06
    没æľīä¸Ģ个
    -0.06
    滩
    -0.06
    尼迪
    -0.06
    éĥİ
    -0.06
    ID
    -0.06
     sou
    -0.05
    ä¿Ĺè¯Ŀ说
    -0.05
    B
    -0.05
    La
    -0.05
    POSITIVE LOGITS
    ãĤ»ãĤ¤
    0.08
    emand
    0.08
    uire
    0.08
    ayah
    0.08
    ugu
    0.08
    acap
    0.08
    azion
    0.08
    /fs
    0.08
    ung
    0.07
    antil
    0.07
    Activations Density 0.002%

    No Known Activations