© 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. 19840
    Prev
    Next
    INDEX
    Explanations

    tight spaces

    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
    èµĭäºĪ
    -0.08
    ä¸ĩ次
    -0.08
    èµĭ
    -0.08
    楼顶
    -0.08
     divisive
    -0.07
    ä¸įåĢ¦
    -0.07
    èī¯
    -0.07
    .expires
    -0.07
    æݺ
    -0.07
    ÙĪاÙĩ
    -0.07
    POSITIVE LOGITS
     space
    0.15
    space
    0.15
    空éĹ´
    0.14
    空éĹ´çļĦ
    0.13
    Space
    0.13
    _space
    0.12
     Space
    0.12
    çļĦ空éĹ´
    0.12
    容纳
    0.12
    空éĸĵ
    0.12
    Activations Density 0.228%

    No Known Activations