© 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. 15278
    Prev
    Next
    INDEX
    Explanations

    solution 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
    AGMA
    -0.09
    管è¾ĸ
    -0.08
    INAL
    -0.07
    ÑģÑĭпа
    -0.07
    ä¸įéĻIJ
    -0.07
    furt
    -0.07
    éĻIJéĢŁ
    -0.07
    infeld
    -0.07
    è¿Ļ个大
    -0.07
    cid
    -0.07
    POSITIVE LOGITS
    ivere
    0.07
     Sturm
    0.07
     rott
    0.07
     UIF
    0.07
    avenport
    0.07
    éĺģ楼
    0.07
     unt
    0.07
    æĮł
    0.06
    ibrary
    0.06
     solutions
    0.06
    Activations Density 0.003%

    No Known Activations