© 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. 46098
    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
    rom
    -0.07
    å¬Ľ
    -0.07
    agt
    -0.06
    æ¬
    -0.06
    ugia
    -0.06
    aket
    -0.06
    æĪ¿éĩĮ
    -0.06
    [:-
    -0.06
    sg
    -0.06
    دÙĩ
    -0.06
    POSITIVE LOGITS
    ضا
    0.07
    WithContext
    0.07
    人åij½
    0.07
    رص
    0.07
    ewriter
    0.07
     Gér
    0.07
    à¹Īà¸Ńà¸ĩ
    0.07
     compilers
    0.07
    åĬĽåĽ¾
    0.07
    erva
    0.07
    Activations Density 0.000%

    No Known Activations