© 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. 55939
    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
    ä¸įå¼ĥ
    -0.07
     Guth
    -0.07
    (fill
    -0.07
    idot
    -0.06
    ä¹ĭä¸į
    -0.06
    çĽĺé¾Ļ
    -0.06
    idis
    -0.06
    uron
    -0.06
    ä¸įä¹ħ
    -0.06
    жек
    -0.06
    POSITIVE LOGITS
    ä¸ĩå²ģ
    0.08
    æijĨ
    0.07
    _truth
    0.07
    çī©è¯Ń
    0.07
    ÑģÑģ
    0.07
    æī®
    0.07
     roundup
    0.07
     RN
    0.06
     cruc
    0.06
    ocr
    0.06
    Activations Density 0.000%

    No Known Activations