© 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. 29816
    Prev
    Next
    INDEX
    Explanations

    documentation and code structure

    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
    eke
    -0.11
    unken
    -0.08
    anza
    -0.08
    lesc
    -0.08
    idis
    -0.08
    交çĶµ
    -0.07
    ä¸Ģåıij
    -0.07
    kiye
    -0.07
    edo
    -0.07
     misk
    -0.07
    POSITIVE LOGITS
     represents
    0.07
     Represents
    0.07
    ãģĹãĤī
    0.07
    åįģ足
    0.07
     representa
    0.07
    代表
    0.07
     representing
    0.07
     represent
    0.06
    尼奥
    0.06
    /target
    0.06
    Activations Density 0.004%

    No Known Activations