© 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. 22594
    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
    lags
    -0.07
     **:**
    -0.06
    Sanders
    -0.06
     **âĸł
    -0.06
    ooks
    -0.06
     panc
    -0.06
    æŁIJ
    -0.06
    ofs
    -0.06
     "**
    -0.06
     übrigens
    -0.06
    POSITIVE LOGITS
    âĢIJ
    0.09
     therein
    0.09
    âĢij
    0.08
    尽享
    0.08
    è¯¥æľº
    0.08
     (âĢ¦)
    0.08
    %E
    0.07
    åľ¨è¯¥
    0.07
    elly
    0.07
    该åĮº
    0.07
    Activations Density 0.000%

    No Known Activations