© 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. 48043
    Prev
    Next
    INDEX
    Explanations

    bone, tooth, vertebrae anatomy

    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
    angers
    -0.07
    åIJĥçĤ¹
    -0.07
    schein
    -0.07
    触å±ı
    -0.07
    æĹłä»¥
    -0.07
    ENCI
    -0.07
    ç¦
    -0.07
    สัà¸ĩà¸ģัà¸Ķ
    -0.07
    黼
    -0.07
    utel
    -0.07
    POSITIVE LOGITS
     sasaran
    0.08
    à°ķà±įà°·
    0.07
    emon
    0.07
    Wide
    0.07
    åħ¬çĽĬäºĭä¸ļ
    0.07
     targeting
    0.07
    éľĢè¦ģåIJĮ
    0.07
     recipient
    0.06
    wide
    0.06
    åĨµ
    0.06
    Activations Density 0.518%

    No Known Activations