© 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. 57176
    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
     пон
    -0.07
    cott
    -0.07
    auer
    -0.07
    essler
    -0.06
    uster
    -0.06
    eu
    -0.06
    olver
    -0.06
    éĢļè¿ĩè¿ĻäºĽ
    -0.06
    iores
    -0.06
    轻伤
    -0.06
    POSITIVE LOGITS
    åIJĮå¿Ĺ为
    0.07
    аÑģÑģив
    0.07
    andes
    0.07
    MT
    0.07
    ights
    0.07
    raul
    0.07
    ighted
    0.07
    .isArray
    0.07
    راÙĩ
    0.07
    Inactive
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.