© 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. 2103
    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
    æľĢåIJİåľ¨
    -0.09
    ingham
    -0.09
    _finalize
    -0.09
    /fw
    -0.09
    finally
    -0.09
    ilhas
    -0.08
    stial
    -0.08
    ervis
    -0.08
    ambre
    -0.08
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    -0.08
    POSITIVE LOGITS
    0.07
     ↵
    0.07
    k
    0.07
     r
    0.07
    ↵
    0.06
     why
    0.06
    igg
    0.06
    à¹Ĥà¸Ĺษ
    0.06
    Why
    0.06
     h
    0.06
    Activations Density 0.000%

    No Known Activations