© 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. 65196
    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
     “
    -0.06
    atz
    -0.06
    S
    -0.05
    è§
    -0.05
    åºĵéĩĮ
    -0.05
     âĢ¦
    -0.05
    à¸ķà¸ģ
    -0.05
    rza
    -0.05
    idel
    -0.05
    âĸ¼
    -0.05
    POSITIVE LOGITS
    amera
    0.08
    ÙĤرر
    0.08
    详ç»Ĩæııè¿°
    0.08
    vertisement
    0.08
    fur
    0.08
    olem
    0.08
    oggled
    0.07
    'user
    0.07
    åįļé³Į
    0.07
     ngưỡng
    0.07
    Activations Density 0.000%

    No Known Activations