© 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. 21875
    Prev
    Next
    INDEX
    Explanations

    questions or parentheses

    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
    éen
    -0.08
    åıĮåĪĽ
    -0.08
    irie
    -0.07
    énk
    -0.07
    ãģ¨ãģĦãģĨãĤĤãģ®
    -0.07
    èĢĮåıĪ
    -0.07
    פש
    -0.07
    ä¸įä½Ĩ
    -0.07
    å·¾
    -0.07
    稽
    -0.07
    POSITIVE LOGITS
    acy
    0.07
    s
    0.07
    ãģĭãģķ
    0.07
    继ç»Ńåħ³æ³¨
    0.06
    osa
    0.06
    ECA
    0.06
    äºĨåįĬ天
    0.06
    æĢ»ä¹ĭ
    0.06
    åįĹå¸Ĥ
    0.06
     habit
    0.06
    Activations Density 0.002%

    No Known Activations