© 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. 62706
    Prev
    Next
    INDEX
    Explanations

    one by one

    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
    odar
    -0.10
    ampler
    -0.08
    adan
    -0.08
    ianos
    -0.07
    ujan
    -0.07
    纯粹
    -0.07
    äºĨä¸Ģå®ļ
    -0.07
    lse
    -0.07
    arin
    -0.07
    _ft
    -0.07
    POSITIVE LOGITS
     từng
    0.14
    éĢIJ
    0.13
    éĢIJ个
    0.13
    éĢIJä¸Ģ
    0.12
    éĢIJ项
    0.12
     progressively
    0.12
    éĢIJæŃ¥
    0.11
     gradually
    0.10
    ä¸Ģ个个
    0.10
    ä¸ĢæŃ¥æŃ¥
    0.10
    Activations Density 0.043%

    No Known Activations