© 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. 27448
    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
    ç¼
    -0.07
    xil
    -0.07
    eo
    -0.07
    æ£ł
    -0.07
    åIJī
    -0.07
    gina
    -0.07
     Gest
    -0.07
    ย
    -0.06
    estig
    -0.06
    nty
    -0.06
    POSITIVE LOGITS
    å±±é«ĺ
    0.08
    游åŃIJ
    0.08
    _LAT
    0.07
    å°Ķæĸ¯
    0.07
    ebru
    0.06
    é¦į
    0.06
    æĪIJåħ¨
    0.06
    innan
    0.06
    æľĽçĿĢ
    0.06
    æĿ¥äºĨ
    0.06
    Activations Density 0.000%

    No Known Activations