© 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. 3711
    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
    ÙĪارÙĩ
    -0.07
    ики
    -0.07
    ×ķ×ĸ
    -0.07
    æºIJ
    -0.07
    ifacts
    -0.07
     Narod
    -0.07
    imulator
    -0.07
    /story
    -0.06
    utusan
    -0.06
    utive
    -0.06
    POSITIVE LOGITS
    perienced
    0.06
     hus
    0.06
    {}",
    0.06
    &T
    0.06
    oured
    0.06
    ads
    0.06
    encv
    0.06
    orio
    0.06
    etter
    0.06
    æľīæĦŁ
    0.06
    Activations Density 0.000%

    No Known Activations