© 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. 42621
    Prev
    Next
    INDEX
    Explanations

    forces and disruptions

    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
    ValuePair
    -0.07
    åľ¨åIJij
    -0.07
    amet
    -0.07
    ä¸Ĭåı¤
    -0.07
    æĹ¥çĶµ
    -0.07
    ði
    -0.07
    æĹ¥ä»İ
    -0.07
    ίνη
    -0.07
    oreach
    -0.07
    å¹¶è¿Ľ
    -0.07
    POSITIVE LOGITS
     sekalipun
    0.10
    ä¾µè¢Ń
    0.08
     gracefully
    0.07
     unfortunate
    0.07
     grâce
    0.07
    agens
    0.07
    Grace
    0.07
     sublicense
    0.07
    ä¸įèĩ³äºİ
    0.07
    -fat
    0.07
    Activations Density 0.120%

    No Known Activations