© 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. 61023
    Prev
    Next
    INDEX
    Explanations

    copy, clone, other

    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
    GetString
    -0.09
    amer
    -0.08
    rab
    -0.08
     Starr
    -0.07
    raum
    -0.07
    å¤ļç§įæĸ¹å¼ı
    -0.07
    大åıij
    -0.07
    èĥ½ä¸º
    -0.07
    åIJijèį£
    -0.07
    .strict
    -0.07
    POSITIVE LOGITS
    åIJĮç±»
    0.09
    åı¯æ¯Ķ
    0.09
    å¤įåĪ¶
    0.08
    ,copy
    0.07
     Copy
    0.07
     copy
    0.07
    åħĦå¼Ł
    0.07
     copying
    0.07
     clone
    0.07
    åIJĮä¸Ģ
    0.07
    Activations Density 0.054%

    No Known Activations