© 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. 27356
    Prev
    Next
    INDEX
    Explanations

    Chinese words and 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
    缸è¾ħ缸æĪIJ
    -0.08
    ä¸Ĭä¸ĢæĿ¡
    -0.08
    éĺ³åİ¿
    -0.07
    ozn
    -0.07
    isz
    -0.07
    çĻ½æ°´
    -0.07
    æ³½æ°ij
    -0.07
    åı¯å¾ª
    -0.07
    agn
    -0.07
    è¾¾
    -0.07
    POSITIVE LOGITS
    idea
    0.08
    nels
    0.08
    oggio
    0.07
    åĽĽä¸ªåŃĹ
    0.07
    en
    0.07
    åľ¨æĢĿæĥ³ä¸Ĭ
    0.07
    .ids
    0.07
    ä¸īéĥ¨
    0.07
    ฯ
    0.06
    aho
    0.06
    Activations Density 0.001%

    No Known Activations