© 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. 22160
    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
    иÑİ
    -0.10
    imini
    -0.10
    asang
    -0.08
    ยาม
    -0.08
    uguay
    -0.08
    _INITIALIZER
    -0.08
    cules
    -0.08
    άÏĤ
    -0.08
    ugins
    -0.08
    jeÄį
    -0.08
    POSITIVE LOGITS
    ï¸ı
    0.11
    ï¸İ
    0.09
    oli
    0.07
    æĢ§è´«è¡Ģ
    0.07
    ol
    0.07
    âĿ
    0.06
    omorphic
    0.06
    ifi
    0.06
    erweise
    0.06
    fully
    0.06
    Activations Density 0.000%

    No Known Activations