© 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. 18761
    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
    ек
    -0.07
     guesses
    -0.06
     [
    -0.06
    eman
    -0.06
    ä¸įæľį
    -0.06
    ys
    -0.06
    é£ĺé£ĺ
    -0.06
     "
    -0.06
    emin
    -0.06
    f
    -0.06
    POSITIVE LOGITS
    ÃľN
    0.09
    .lu
    0.08
    ÙıÙĦ
    0.08
    (ti
    0.08
    ampoline
    0.08
    ietf
    0.08
    пок
    0.08
    stück
    0.08
    uille
    0.08
    -await
    0.08
    Activations Density 0.000%

    No Known Activations