© 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. 45802
    Prev
    Next
    INDEX
    Explanations

    end punctuation

    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
    ег
    -0.08
    imi
    -0.08
    ÃŃst
    -0.08
    ici
    -0.08
    ivu
    -0.07
    ä¸ĭä¸Ģç«ł
    -0.07
    piel
    -0.07
    ãĤ®ãĥ¼
    -0.07
     Goldberg
    -0.07
    æĪij们èĩªå·±
    -0.07
    POSITIVE LOGITS
    \:
    0.06
     hailed
    0.06
    åĪ©åĻ¨
    0.06
     Lovely
    0.06
    ï¿
    0.06
    anke
    0.06
    odate
    0.06
    /bit
    0.06
    terra
    0.06
    çıŃéĩĮ
    0.05
    Activations Density 0.002%

    No Known Activations