© 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. 26517
    Prev
    Next
    INDEX
    Explanations

    hen has

    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
     something
    -0.06
    hap
    -0.06
    -0.06
     Something
    -0.06
     in
    -0.05
    if
    -0.05
    è»
    -0.05
    åľ°åIJij
    -0.05
     Wel
    -0.05
    udel
    -0.05
    POSITIVE LOGITS
    çļĦè¿Ļä¸Ģ
    0.11
    è¿Ļçķª
    0.11
    è¿Ļæł·è¯´
    0.10
    è¿Ļä¹Ī说
    0.10
    æīĢæĮĩ
    0.09
    çļĦè¿Ļ个
    0.09
    å¦ĤæѤ
    0.09
    è¿Ļä¹Ī
    0.09
    è¿Ļè¯Ŀ
    0.09
    å¤įåĪ¶éĵ¾æİ¥
    0.09
    Activations Density 0.107%

    No Known Activations