© 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. 40274
    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
    ufr
    -0.07
    ä¹ĭä¸į
    -0.07
     Chair
    -0.07
    ilda
    -0.06
    æĹłä»İ
    -0.06
    LET
    -0.06
     uptake
    -0.06
    .gnu
    -0.06
    Scale
    -0.06
    _scale
    -0.06
    POSITIVE LOGITS
     каÑģа
    0.07
    å¾·åŁº
    0.07
    ãģ£ãģĵ
    0.07
    indle
    0.07
    ä¸Ģèµ·åĪĨ享
    0.07
    éĤ»
    0.06
    resses
    0.06
    çļĦè¿ĺæĺ¯
    0.06
    cident
    0.06
    IVATE
    0.06
    Activations Density 0.000%

    No Known Activations