© 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. 62663
    Prev
    Next
    INDEX
    Explanations

    years

    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
    æ¯ı天éĥ½åľ¨
    -0.07
    åįģç«ł
    -0.07
    åģļçļĦå°±æĺ¯
    -0.07
    chave
    -0.07
    engers
    -0.07
    send
    -0.07
    å¹´èĩ³ä»Ĭ
    -0.07
    çİ°åľ¨å°±
    -0.07
    .platform
    -0.07
    ators
    -0.07
    POSITIVE LOGITS
    kee
    0.07
    åĨķ
    0.07
    ister
    0.07
    angi
    0.07
    æľī天
    0.06
    æijĶè·¤
    0.06
    edition
    0.06
     Murphy
    0.06
    aca
    0.06
    æŃ¥åŃIJ
    0.06
    Activations Density 0.046%

    No Known Activations