© 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. 64572
    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
    issage
    -0.08
    åIJĦé¡¹å·¥ä½ľä»»åĬ¡
    -0.08
    éĩij森
    -0.08
    TEMPL
    -0.08
    çŃīäºĭ项
    -0.08
    chnik
    -0.07
    æŁ¥çľĭæĽ´å¤ļä¿¡æģ¯
    -0.07
    æŁ¥çľĭæĽ´å¤ļ
    -0.07
    ÃŃnu
    -0.07
    ynet
    -0.07
    POSITIVE LOGITS
    blo
    0.06
    ä¸Ģè¾¹
    0.06
    tern
    0.06
    æĵħ
    0.06
    TRA
    0.06
    aho
    0.06
    ä¹ĭçªĹ
    0.06
    æŀģåĬĽ
    0.06
    coder
    0.06
    ona
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.