© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 25072
    Prev
    Next
    INDEX
    Explanations

    rewriting or transforming something

    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
    ickers
    -0.07
     scaled
    -0.07
     estimated
    -0.07
    scaled
    -0.07
    éĵ¡
    -0.07
    retry
    -0.06
    estimated
    -0.06
     Border
    -0.06
    ÑĢода
    -0.06
    Border
    -0.06
    POSITIVE LOGITS
     transformations
    0.13
     rewrite
    0.12
     transformation
    0.12
    _rewrite
    0.11
     rewriting
    0.11
    转åĮĸ
    0.11
     rearr
    0.10
    rewrite
    0.10
     transforms
    0.10
     rew
    0.10
    Activations Density 0.055%

    No Known Activations