© 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. 39603
    Prev
    Next
    INDEX
    Explanations

    . followed by sentence starters

    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
     faud
    -0.08
    Occurred
    -0.07
    åŃĿ
    -0.07
    cntl
    -0.07
    åĨįè§ģ
    -0.07
     Dafür
    -0.07
    .mozilla
    -0.07
    ForKey
    -0.07
    Ŀ¼
    -0.07
    itati
    -0.07
    POSITIVE LOGITS
    apel
    0.08
    æĦıä¹īçļĦ
    0.07
    为ä»Ģä¹Ī说
    0.07
    [data
    0.06
    .strings
    0.06
    åĴĮæĦıä¹ī
    0.06
     Hath
    0.06
    ång
    0.06
     paper
    0.06
    æĦıä¹ī
    0.06
    Activations Density 0.113%

    No Known Activations