© 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. 2032
    Prev
    Next
    INDEX
    Explanations

    code execution prompts

    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
    å¼ķ
    -0.07
    éĢļè¿ĩåŃ¦ä¹ł
    -0.07
     bang
    -0.06
    åľ°äºļ
    -0.06
     generalized
    -0.06
    çĤ¹åĩ»ä¸ĭæĸ¹
    -0.06
     Brothers
    -0.06
    pare
    -0.06
     obviously
    -0.06
    Bro
    -0.06
    POSITIVE LOGITS
    åĨį次
    0.09
    AGAIN
    0.08
    empo
    0.08
    补缺
    0.08
    renom
    0.08
    uname
    0.07
    éĢ²ä¸ĢæŃ¥
    0.07
    ICAST
    0.07
     Fass
    0.07
    æµ·é»ĺ
    0.07
    Activations Density 0.005%

    No Known Activations