© 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. 32127
    Prev
    Next
    INDEX
    Explanations

    transforming or transformation

    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
    æľªè¢«
    -0.10
    íĥĿ
    -0.08
    没æľī被
    -0.08
    attach
    -0.08
    rent
    -0.08
    ãģ®ãģ¾ãģ¾
    -0.08
    Attach
    -0.07
     Attach
    -0.07
    æĭĽ
    -0.07
    æĮģä¹ĭ以
    -0.07
    POSITIVE LOGITS
     smoothing
    0.11
     transformation
    0.11
    transform
    0.11
     transforming
    0.10
     transform
    0.10
     transforms
    0.10
    .transform
    0.10
     transforma
    0.10
     Transform
    0.10
    Transformation
    0.10
    Activations Density 0.194%

    No Known Activations