© 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. 31355
    Prev
    Next
    INDEX
    Explanations

    either or

    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
    andest
    -0.08
    RIES
    -0.07
    urve
    -0.07
     Putra
    -0.07
    omic
    -0.07
    两æīĭ
    -0.06
    伯
    -0.06
    æ½
    -0.06
    ARSE
    -0.06
    uston
    -0.06
    POSITIVE LOGITS
     either
    0.20
    either
    0.20
     Either
    0.18
    Either
    0.17
    è¦ģä¹Īæĺ¯
    0.16
    è¦ģä¹Ī
    0.16
     entweder
    0.16
     Ø¥Ùħا
    0.14
     EITHER
    0.14
    ä»»ä½ķä¸Ģæĸ¹
    0.14
    Activations Density 0.122%

    No Known Activations