© 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. 51185
    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
    ryp
    -0.08
    jang
    -0.07
    urable
    -0.07
    æĿĢ
    -0.07
    chio
    -0.07
    oken
    -0.07
    endr
    -0.07
    chow
    -0.07
    _due
    -0.07
    theon
    -0.07
    POSITIVE LOGITS
    -debug
    0.08
    irket
    0.07
    ental
    0.07
     profiling
    0.07
    itter
    0.07
    rof
    0.06
    isks
    0.06
     debug
    0.06
     Griffin
    0.06
    ims
    0.06
    Activations Density 0.000%

    No Known Activations