© 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. 19277
    Prev
    Next
    INDEX
    Explanations

    is/are followed by descriptive words

    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
    ä¸Ģèµ·
    -0.08
    ze
    -0.07
    åIJĮåľ¨
    -0.07
    åı«
    -0.07
    å½°
    -0.07
    cko
    -0.07
    ukk
    -0.07
    éģĶãģ¯
    -0.07
    Ø´Ùĩد
    -0.07
    èĢĮåĸ»
    -0.07
    POSITIVE LOGITS
     indeed
    0.08
    ä¹ĭæīĢ以
    0.08
     therefore
    0.08
    ëĦIJ
    0.07
    æīĢæľīè¿ĻäºĽ
    0.07
     neither
    0.07
     primarily
    0.07
     often
    0.07
    åĩŃåĢŁåħ¶
    0.07
    \<^
    0.07
    Activations Density 0.241%

    No Known Activations