© 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. 63552
    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
    orgh
    -0.07
    æľ¬çīĪ
    -0.06
     reg
    -0.06
     sortable
    -0.06
    å°ıåĮºåĨħ
    -0.06
     Jon
    -0.06
    åĢļ
    -0.06
    disposed
    -0.06
     amongst
    -0.06
    æĺĮå¹³
    -0.06
    POSITIVE LOGITS
    æ²³éķĩ
    0.07
    ölt
    0.07
     rifl
    0.07
    iente
    0.07
    ç»ĻåĩºçļĦ
    0.07
     _______,
    0.07
    é¦ĸ
    0.07
    ulas
    0.07
    wand
    0.07
    åľ³
    0.06
    Activations Density 0.000%

    No Known Activations