© 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. 3189
    Prev
    Next
    INDEX
    Explanations

    Adobe creative and development applications

    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
    æ²IJæµ´
    -0.07
    ç©¿ä¸Ĭ
    -0.06
     forward
    -0.06
     reliably
    -0.06
     Implementation
    -0.06
     trickle
    -0.06
     hairy
    -0.06
     reliability
    -0.06
    otal
    -0.06
    å·¥ç¨ĭå¸ĪæĭĽèģĺ
    -0.06
    POSITIVE LOGITS
    .exe
    0.10
     thao
    0.10
    Adobe
    0.10
     ìŀijìĹħ
    0.10
     editing
    0.10
     Photoshop
    0.10
    editing
    0.10
     Adobe
    0.09
    desktop
    0.09
    ä½ľæ¥Ń
    0.09
    Activations Density 0.402%

    No Known Activations