© 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. 27479
    Prev
    Next
    INDEX
    Explanations

    show that

    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
    åıªåĽł
    -0.06
     Lyn
    -0.06
    oric
    -0.06
    ort
    -0.06
    æĺ¯åŁºäºİ
    -0.06
    æĬ½åĩº
    -0.06
    åıªæĺ¯åĽłä¸º
    -0.06
    sn
    -0.06
    èĬ³
    -0.06
    /
    -0.06
    POSITIVE LOGITS
    echt
    0.08
    owitz
    0.07
    quential
    0.07
    Ùİاع
    0.07
     иÑģк
    0.07
    cade
    0.07
    微信æľĭåıĭåľĪ
    0.07
    _INCREMENT
    0.07
    .za
    0.07
    æ¯ıä¸Ģä½į
    0.07
    Activations Density 0.018%

    No Known Activations