© 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. 12679
    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
    /browser
    -0.08
    eper
    -0.08
    eping
    -0.07
    Ñģнабжение
    -0.07
    Thunk
    -0.07
    ubble
    -0.07
     unmist
    -0.07
    ãĤ¹ãĥ¡
    -0.07
    è¦ģå¦Ĥä½ķ
    -0.07
    irme
    -0.07
    POSITIVE LOGITS
    omatis
    0.08
    зам
    0.07
    oggio
    0.06
     none
    0.06
    ¬
    0.06
    est
    0.06
    åīį身
    0.06
    ubro
    0.06
    .react
    0.06
    æĻļäºĨ
    0.06
    Activations Density 0.000%

    No Known Activations