© 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. 12179
    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
    regar
    -0.08
     lut
    -0.07
     Dash
    -0.07
    egal
    -0.07
     ÐĽÑĥг
    -0.07
    éĿ
    -0.07
     $($
    -0.07
    á»ijt
    -0.07
    isia
    -0.07
     lul
    -0.07
    POSITIVE LOGITS
    ×ŀ×Ļ×Ŀ
    0.07
    usses
    0.07
    ŀ
    0.06
     share
    0.06
    飯
    0.06
    èĴĻå¾·
    0.06
    åħ¥å®¤
    0.06
    illés
    0.06
    [((
    0.06
    htub
    0.06
    Activations Density 0.000%

    No Known Activations