© 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. 1369
    Prev
    Next
    INDEX
    Explanations

    transform, translate, rotate, migration

    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
    éĻ·
    -0.09
    ç»ĵ
    -0.08
    æĿł
    -0.08
    spel
    -0.08
    è°
    -0.08
    å¾ĺå¾Ĭ
    -0.07
    åĪĹ
    -0.07
    izen
    -0.07
    åĩºä¸į
    -0.07
    ç»ĵäºĨ
    -0.07
    POSITIVE LOGITS
     relocate
    0.08
    平移
    0.08
    irian
    0.08
    odon
    0.08
     reloc
    0.07
    ยà¹īาย
    0.07
     transformation
    0.07
    transform
    0.07
    åĩ¡
    0.07
     transformative
    0.07
    Activations Density 0.001%

    No Known Activations