© 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. 34145
    Prev
    Next
    INDEX
    Explanations

    imitation, mimicry, copying

    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
    ened
    -0.08
    mans
    -0.08
    tenham
    -0.08
    taire
    -0.08
    wick
    -0.07
    åħ³äºİè¿Ľä¸ĢæŃ¥
    -0.07
    endid
    -0.07
    abase
    -0.07
    æ¢Ĩ
    -0.07
    รà¸Ńà¸Ķ
    -0.07
    POSITIVE LOGITS
    /cop
    0.13
    模仿
    0.13
    å¤įåĪ¶
    0.13
    roring
    0.12
     imitation
    0.11
     copying
    0.10
     copy
    0.10
     mimic
    0.10
    仿
    0.10
     mim
    0.09
    Activations Density 0.097%

    No Known Activations