© 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. 51372
    Prev
    Next
    INDEX
    Explanations

    dimensional data or 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
    è¡Įäºij
    -0.07
     reverse
    -0.07
     revers
    -0.07
    éĥ¨åĪĨçļĦ
    -0.07
    ottie
    -0.07
    æľªå¤®
    -0.06
    åįıè®®çļĦ
    -0.06
    hle
    -0.06
    mee
    -0.06
    å²ģå²ģ
    -0.06
    POSITIVE LOGITS
    维度
    0.10
     space
    0.09
    空éĹ´
    0.09
    å¤ļç»´
    0.09
     dimensions
    0.09
     dimension
    0.09
     пÑĢоÑģÑĤÑĢанÑģÑĤво
    0.09
    空éĹ´åĴĮ
    0.09
    spaces
    0.09
    space
    0.09
    Activations Density 0.026%

    No Known Activations