© 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. 39602
    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
    card
    -0.08
    chera
    -0.08
    æĢ»æĺ¯åľ¨
    -0.07
    符
    -0.07
    otto
    -0.07
    cardo
    -0.07
    алÑĮÑı
    -0.07
    ovol
    -0.07
     Heads
    -0.07
    <tag
    -0.07
    POSITIVE LOGITS
    hq
    0.07
    大麦
    0.07
    us
    0.07
    ese
    0.06
     brushed
    0.06
    hind
    0.06
     brushes
    0.06
    ä¸Ńä¹ĭ
    0.06
    ')==
    0.06
    usal
    0.06
    Activations Density 0.000%

    No Known Activations