© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 10655
    Prev
    Next
    INDEX
    Explanations

    space or whitespace

    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
    å¸ĪçļĦ
    -0.08
    deen
    -0.08
    bruck
    -0.07
    ä¸įè¡°
    -0.07
     cáp
    -0.07
    iov
    -0.07
    ovo
    -0.07
    ¶
    -0.07
    å°ĸçļĦ
    -0.07
    æľĢå¿«çļĦéĢŁåº¦
    -0.07
    POSITIVE LOGITS
     spaces
    0.09
    isspace
    0.08
     Spaces
    0.08
    spaces
    0.08
    space
    0.08
    _SPACE
    0.08
    .space
    0.08
     space
    0.08
    ä½Ļåľ°
    0.07
    (space
    0.07
    Activations Density 0.055%

    No Known Activations