© 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. 2956
    Prev
    Next
    INDEX
    Explanations

    biliary duct, gallbladder, bile

    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
    iliz
    -0.08
    aty
    -0.07
    EXP
    -0.07
    /exp
    -0.07
    cord
    -0.07
    ç¥ī
    -0.07
    大西æ´ĭ
    -0.07
    å±¹
    -0.07
    踵
    -0.07
    å¯Ĩå¯Ĩ
    -0.06
    POSITIVE LOGITS
    èĥĨåĽĬ
    0.10
    èĥĨæ±ģ
    0.09
     bile
    0.09
     bilir
    0.09
     gall
    0.08
    episode
    0.08
    bile
    0.08
     Ñħоле
    0.08
     cst
    0.08
    eshire
    0.08
    Activations Density 0.082%

    No Known Activations