© 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. 57742
    Prev
    Next
    INDEX
    Explanations

    counts or numbers

    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
     ÑĢаÑģп
    -0.07
     ga
    -0.07
     RES
    -0.06
     www
    -0.06
    ledge
    -0.06
    ve
    -0.06
    cik
    -0.06
     ink
    -0.06
    帷
    -0.06
    å±¥åİĨ
    -0.06
    POSITIVE LOGITS
    æĢ»è®¡
    0.10
    åIJĪè¨Ī
    0.09
    è´¡çĮ®
    0.09
    -category
    0.09
    åIJĪ计
    0.09
    .addAll
    0.09
    åħ±è®¡
    0.09
     kateg
    0.09
    两类
    0.09
    æĢ»åħ±
    0.09
    Activations Density 0.001%

    No Known Activations