© 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. 26246
    Prev
    Next
    INDEX
    Explanations

    case document numbers

    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
    ryn
    -0.09
    ye
    -0.08
    ain
    -0.07
    anyag
    -0.07
    交æį¢
    -0.07
    thur
    -0.06
     Uk
    -0.06
    aine
    -0.06
    aw
    -0.06
    交æıĽ
    -0.06
    POSITIVE LOGITS
    publisher
    0.07
    luan
    0.07
    trieb
    0.07
    鸳
    0.07
    ModelState
    0.07
    _procs
    0.07
    åĭĺ
    0.06
    ebook
    0.06
    Äħd
    0.06
    Sizer
    0.06
    Activations Density 0.153%

    No Known Activations