© 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. 41161
    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
     충
    -0.07
    áĥIJáĥĻ
    -0.07
    orama
    -0.07
    æľ¬å¹´
    -0.07
     hop
    -0.07
    rang
    -0.07
     bush
    -0.07
    头
    -0.07
    宿
    -0.07
    arest
    -0.06
    POSITIVE LOGITS
    å¾Ĺæīĭ
    0.07
     papar
    0.07
    صر
    0.07
    
    0.06
    er
    0.06
    ë¦Ħ
    0.06
    cla
    0.06
    uson
    0.06
    ìĸ
    0.06
    åħ¶èº«
    0.06
    Activations Density 0.000%

    No Known Activations