© 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. 41622
    Prev
    Next
    INDEX
    Explanations

    physical objects and space

    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
    اÙħÙĬØ©
    -0.08
    èĤ¡
    -0.08
    两åı£
    -0.07
    unnel
    -0.07
    油箱
    -0.07
    åĺ´è¾¹
    -0.07
    åı£å¾Ħ
    -0.07
     اÙĦÙģر
    -0.07
    .High
    -0.07
    æīĭå¿ĥ
    -0.07
    POSITIVE LOGITS
    çī©ä½ĵ
    0.12
    çī©ä½ĵçļĦ
    0.11
    ä¹ĭçī©
    0.10
     objects
    0.10
    å®ŀçī©
    0.09
     physical
    0.09
    çļĦçī©çIJĨ
    0.09
    å®ŀä½ĵ
    0.09
    วัà¸ķà¸ĸุ
    0.09
     object
    0.09
    Activations Density 0.037%

    No Known Activations