© 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. 61350
    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
    没æľīå¿ħè¦ģ
    -0.08
    uger
    -0.07
    lain
    -0.07
    éia
    -0.07
    强è°ĥçļĦæĺ¯
    -0.07
    egr
    -0.07
    á»ı
    -0.07
    گرÛĮ
    -0.07
    izin
    -0.07
    åŃĺæľī
    -0.07
    POSITIVE LOGITS
    ç¼ļ
    0.07
    çĨŁ
    0.07
    举æīĭ
    0.07
    人人éĥ½
    0.07
    ä¸Ģèĩ³
    0.06
     Sond
    0.06
    人æĪĸ
    0.06
    èĪĨ
    0.06
    èķī
    0.06
    ipt
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.