© 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. 37906
    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
    åıįæĶ»
    -0.08
    cycle
    -0.07
    å¤ļåıij
    -0.07
    cam
    -0.07
    æľĢæĸ°æĸĩç«ł
    -0.07
    undra
    -0.07
    icali
    -0.07
    訴
    -0.07
    klus
    -0.07
    å§Ĭ妹
    -0.07
    POSITIVE LOGITS
    åľ¨è§Ħå®ļ
    0.07
     iam
    0.07
    reference
    0.07
    尺度
    0.07
    æĸ¹å¼ı使çĶ¨
    0.07
     SCALE
    0.07
    é«ĺæłĩåĩĨ
    0.07
    ilde
    0.07
    æľīä½į
    0.07
    æł¼åŃIJ
    0.06
    Activations Density 0.000%

    No Known Activations