© 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. 58245
    Prev
    Next
    INDEX
    Explanations

    locations relative to flow or position

    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
    _utilities
    -0.07
     complement
    -0.07
    alle
    -0.07
    å©¢
    -0.07
    Corner
    -0.07
    .paths
    -0.07
    æĹı
    -0.07
    æĭĤ
    -0.07
    osu
    -0.07
    iero
    -0.07
    POSITIVE LOGITS
    段çļĦ
    0.16
    段
    0.16
    路段
    0.14
     Äijoạn
    0.14
    ä¸Ń段
    0.13
    ä¸ī段
    0.13
    åĪĨ段
    0.13
    ä¸Ģ段
    0.13
    两段
    0.12
     segments
    0.12
    Activations Density 0.429%

    No Known Activations