© 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. 57734
    Prev
    Next
    INDEX
    Explanations

    connected and contiguous

    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
    å¾Ģåīį
    -0.07
     setting
    -0.07
    ä¸Ģå¼ı
    -0.07
    硬
    -0.07
    çªĦ
    -0.07
    åĩĮ
    -0.07
    ä¸Ģ级
    -0.07
    åīįåįĬ
    -0.07
     gears
    -0.07
    çĭł
    -0.07
    POSITIVE LOGITS
    è¿ŀéĢļ
    0.12
     connectivity
    0.11
    connected
    0.10
     contiguous
    0.10
     connected
    0.09
    缸è¿ŀ
    0.09
    èģĶéĢļ
    0.09
     Connectivity
    0.09
     isConnected
    0.09
    èĶĵ延
    0.09
    Activations Density 0.019%

    No Known Activations