© 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. 51061
    Prev
    Next
    INDEX
    Explanations

    spatial arrangements and locations

    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
    èĬ¸
    -0.07
    ä¸įæį¢
    -0.07
    Divider
    -0.07
    æį¢
    -0.07
     Ahead
    -0.07
    .levels
    -0.07
    åĴĮ丰å¯ĮçļĦ
    -0.07
    ibar
    -0.07
    ä¾Ŀ次为
    -0.06
    æıĽ
    -0.06
    POSITIVE LOGITS
     locations
    0.13
    两å¤Ħ
    0.11
     Locations
    0.11
    åĪĨæķ£
    0.10
     spread
    0.10
     scattered
    0.10
    Locations
    0.10
    locations
    0.10
    åĽĽå¤Ħ
    0.10
    _locations
    0.09
    Activations Density 0.017%

    No Known Activations