© 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. 41649
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æīĢ欲
    -0.07
    c
    -0.07
    串
    -0.07
    à¹ģวà¸Ķลà¹īà¸Ńม
    -0.06
    å±¥
    -0.06
    å°ıç¼ĸ
    -0.06
    æľ¬çĿĢ
    -0.06
     Ebony
    -0.06
    is
    -0.06
    ikit
    -0.06
    POSITIVE LOGITS
    abia
    0.09
    bió
    0.08
    ä¸Ģç½ij
    0.08
    chsel
    0.08
    ANTE
    0.07
    åŁĶ
    0.07
    ảnh
    0.07
    ãĤ¿ãĤ¤ãĥł
    0.07
    åĴĮèĶ¼
    0.07
    lyph
    0.07
    Activations Density 0.000%

    No Known Activations