© 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. 13956
    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
    arma
    -0.09
    æľ¬ç½ij
    -0.08
    arin
    -0.08
    èĸ
    -0.07
    éŨå¸Ĥ
    -0.07
     campe
    -0.07
    奸
    -0.07
    iclass
    -0.07
    Äĥt
    -0.07
    åĮ»åѦè§Ĥå¯Ł
    -0.07
    POSITIVE LOGITS
    ing
    0.07
    istrator
    0.07
    å§Ĩæĸ¯
    0.06
    aths
    0.06
    orios
    0.06
    wszy
    0.06
    ffel
    0.06
    TTY
    0.06
    ofer
    0.06
    åIJģ
    0.06
    Activations Density 0.000%

    No Known Activations