© 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. 46650
    Prev
    Next
    INDEX
    Explanations

    table delimiters

    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
    a
    -0.07
    -0.07
    Âł
    -0.07
    ci
    -0.07
    cs
    -0.07
    aan
    -0.07
    an
    -0.06
    ly
    -0.06
    sa
    -0.06
    kan
    -0.06
    POSITIVE LOGITS
    æĽ²å¼ł
    0.09
    ê·Ģ
    0.09
    gup
    0.08
    å¾ĢæľŁåĽŀ顾
    0.08
    heimer
    0.08
    æľĢæĸ°ç«łèĬĤ
    0.08
    klet
    0.08
    åĭĩå¾Ģ缴åīį
    0.08
    erville
    0.08
    éĺ¿æĭī伯
    0.08
    Activations Density 0.015%

    No Known Activations