© 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. 60347
    Prev
    Next
    INDEX
    Explanations

    dependent, constant, expression

    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
    åĬłå¼ºåŃ¦ä¹ł
    -0.07
    зе
    -0.07
    adesh
    -0.07
    微信æī«ä¸Ģæī«
    -0.07
    ZA
    -0.07
    lepas
    -0.07
    kün
    -0.07
    maak
    -0.07
    èĢħä¼ĺåħĪ
    -0.07
    antan
    -0.07
    POSITIVE LOGITS
    çħ¦
    0.09
    åĽłä¸ºå®ĥ
    0.08
    å±ħå¤ļ
    0.07
    åĽłä¸ºä½ł
    0.07
    åĽłä¸ºå¥¹
    0.07
    ois
    0.07
     unless
    0.07
    主è¦ģ表çİ°åľ¨
    0.07
     because
    0.07
    åĽłä¸ºä»ĸ
    0.07
    Activations Density 0.020%

    No Known Activations