© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22967
    Prev
    Next
    INDEX
    Explanations

    outer edge or surrounding wall

    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
    桥头
    -0.08
    æ¡¥ä¸Ĭ
    -0.07
    jit
    -0.07
    éŨåīį
    -0.07
    headed
    -0.07
     ÑĨенÑĤÑĢа
    -0.07
    Bridge
    -0.06
     underline
    -0.06
    èĮħ
    -0.06
     Centrale
    -0.06
    POSITIVE LOGITS
    çݯç»ķ
    0.16
     surrounding
    0.16
    ä¸ĢåľĪ
    0.16
    åĽ´
    0.16
    åĮħåĽ´
    0.15
    äºĨä¸ĢåľĪ
    0.15
    åĽ´ç»ķ
    0.15
     outer
    0.15
     surrounds
    0.15
     enclosing
    0.15
    Activations Density 0.203%

    No Known Activations