© 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. 11491
    Prev
    Next
    INDEX
    Explanations

    awards open for entries

    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
    åŃĺæľī
    -0.07
     nas
    -0.07
    thon
    -0.07
    åijĬè¯īæĪij
    -0.07
    è§ģéĿ¢ä¼ļ
    -0.06
    大åī§éĻ¢
    -0.06
    itzer
    -0.06
    çľĭè§ģ
    -0.06
    äºĨä¸Ģåı¥
    -0.06
    รà¸ĩ
    -0.06
    POSITIVE LOGITS
    usso
    0.08
    nder
    0.08
    обÑĢа
    0.07
    ept
    0.07
    åıijå±ķæĪIJ为
    0.07
    nel
    0.07
    alarına
    0.07
    åıijå±ķæĸ¹åIJij
    0.07
    解åĨ³è¿Ļ个éĹ®é¢ĺ
    0.07
    åıijå±ķ模å¼ı
    0.07
    Activations Density 0.001%

    No Known Activations