© 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. 17256
    Prev
    Next
    INDEX
    Explanations

    Chinese characters

    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
    ạt
    -0.08
    èij©
    -0.08
    桦
    -0.07
    éĩijé¦Ļ
    -0.07
    ä¿ĥ
    -0.07
    ần
    -0.07
     вкладÑĭ
    -0.07
    èĮī
    -0.07
    ubar
    -0.07
    ä¸Ģä¾ĭ
    -0.07
    POSITIVE LOGITS
    äºĮä¸ī
    0.07
    äºĮæĺ¯
    0.07
    asc
    0.07
     Duy
    0.07
    ulse
    0.07
    asca
    0.07
    å¼Ĥ
    0.06
    ç§ijæĬĢèĤ¡ä»½æľīéĻIJåħ¬åı¸
    0.06
    è¶
    0.06
    ëĭĪ
    0.06
    Activations Density 0.004%

    No Known Activations