© 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. 26864
    Prev
    Next
    INDEX
    Explanations

    extension or extends

    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
    OrElse
    -0.07
    alan
    -0.07
    贯穿äºİ
    -0.07
    Dash
    -0.06
    åľ¨ä»ĬåIJİçļĦå·¥ä½ľä¸Ń
    -0.06
    adder
    -0.06
     conc
    -0.06
    ium
    -0.06
    (contents
    -0.06
    iro
    -0.06
    POSITIVE LOGITS
    chetto
    0.07
    æī¿
    0.07
    æ°´æĺ¯
    0.07
    epage
    0.07
    ë³ij
    0.07
    åĽŀåIJĪ
    0.07
    çŃĶ主
    0.07
    TypeInfo
    0.07
     INV
    0.07
    纯水
    0.07
    Activations Density 0.006%

    No Known Activations