© 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. 21495
    Prev
    Next
    INDEX
    Explanations

    not only, nor

    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
    luv
    -0.09
    åĪ°ä¸Ģ个
    -0.08
    ught
    -0.08
    åħ¬åı¸æĭ¥æľī
    -0.08
    ync
    -0.08
    ãĤĭãģ¨ãģį
    -0.07
    ucu
    -0.07
    ê»ı
    -0.07
    itated
    -0.07
    ucer
    -0.07
    POSITIVE LOGITS
     have
    0.10
     is
    0.09
    ìĿĺ
    0.08
     are
    0.08
    çļĦ
    0.08
    çļĦæĪij
    0.08
    ï¸ı
    0.07
     has
    0.07
     be
    0.07
     είναι
    0.07
    Activations Density 0.087%

    No Known Activations