© 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. 27314
    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
    Ð¢ÐŁ
    -0.07
    utzer
    -0.07
    клÑİ
    -0.07
    éļıå¤Ħ
    -0.07
    ány
    -0.07
    æĩĤäºĨ
    -0.07
    ocks
    -0.07
    æĤ¨å¥½
    -0.07
    okia
    -0.06
    úc
    -0.06
    POSITIVE LOGITS
     Bellev
    0.07
    writing
    0.07
    atory
    0.07
    åĽ½ä¹ĭ
    0.07
    ific
    0.07
    ador
    0.07
    lep
    0.07
    ä½ľçŃĶ
    0.07
    ubil
    0.06
    cre
    0.06
    Activations Density 0.000%

    No Known Activations