© 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. 61507
    Prev
    Next
    INDEX
    Explanations

    oceans and seas

    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
    河边
    -0.07
    elog
    -0.07
    ifter
    -0.07
    è¿ĩæ²³
    -0.07
    æīĽ
    -0.07
    åĩºè´¨
    -0.07
    ked
    -0.07
    æ±Łè¾¹
    -0.06
    ä¸´æ±Ł
    -0.06
    /function
    -0.06
    POSITIVE LOGITS
    -facing
    0.11
    ä¸Ĭ空
    0.09
    orda
    0.08
    浩çĢļ
    0.08
     circulation
    0.07
    inian
    0.07
    reopen
    0.07
    诸
    0.07
    -wide
    0.07
     unnamed
    0.07
    Activations Density 0.037%

    No Known Activations