© 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. 57607
    Prev
    Next
    INDEX
    Explanations

    compound words or phrases

    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
    å®¶åľ¨
    -0.06
    å¹´åºķåīį
    -0.06
    åįģç«ł
    -0.06
    åľ¨äº¬
    -0.06
     sey
    -0.06
    ÙĪست
    -0.06
    家
    -0.06
    :?
    -0.06
    åį³åľ¨
    -0.06
     عÙħÙĪÙħ
    -0.06
    POSITIVE LOGITS
     genannte
    0.08
    åĺİ
    0.08
    inese
    0.08
    INCI
    0.07
    æĪij们çļĦå·¥ä½ľ
    0.07
    qi
    0.07
    羣æŃ£åľ°
    0.07
    ezen
    0.07
    hoto
    0.07
    /we
    0.07
    Activations Density 0.734%

    No Known Activations