© 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. 61516
    Prev
    Next
    INDEX
    Explanations

    depth level distance

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    å¸ĤåĢ¼
    -0.08
    -handle
    -0.08
    约åįł
    -0.08
    à¸Ħืà¸Ļ
    -0.08
    大åIJī
    -0.08
    ampang
    -0.08
    并æĮīçħ§
    -0.08
     khâu
    -0.07
     Lump
    -0.07
    avern
    -0.07
    POSITIVE LOGITS
     distance
    0.07
     assigned
    0.07
    æľĢéķ¿çļĦ
    0.07
    è·Ŀ离
    0.07
    èĬ½
    0.07
    æľĢçŁŃ
    0.07
    ç½ļ
    0.06
    distance
    0.06
    eres
    0.06
    çļĦè·Ŀ离
    0.06
    Activations Density 0.016%

    No Known Activations