© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 50094
    Prev
    Next
    INDEX
    Explanations

    clothing brand or industry

    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
    å°ıæĿ¿
    -0.08
    çĽ¾
    -0.07
    alous
    -0.07
     вда
    -0.07
    被å°ģ
    -0.07
    çĴĭ
    -0.07
    çľ¼çľ¶
    -0.07
     capped
    -0.07
    ional
    -0.06
    ublisher
    -0.06
    POSITIVE LOGITS
    éŀĭ帽
    0.10
    ä¸Ģ件
    0.09
     worn
    0.09
    纯æ£ī
    0.09
     одеждÑĭ
    0.09
    аниÑĨ
    0.08
    ลาย
    0.08
    å°ºçłģ
    0.08
    ucci
    0.08
    橱
    0.08
    Activations Density 0.153%

    No Known Activations