© 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. 11162
    Prev
    Next
    INDEX
    Explanations

    digits and symbols

    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
     (...)
    -0.07
    ousse
    -0.07
    áĥķáĥľ
    -0.06
    æľīåħ¶
    -0.06
    æľ¬åįķä½į
    -0.06
    éĩıå°ij
    -0.06
    ål
    -0.06
    iani
    -0.06
    elius
    -0.06
     Tief
    -0.06
    POSITIVE LOGITS
    ãģĺãĤģãģ¦
    0.07
    ırı
    0.07
    itarian
    0.07
    лиÑĨа
    0.07
    ï¸İ
    0.06
    éĢĻæĻĤåĢĻ
    0.06
    dbg
    0.06
    è¿ĩçļĦ
    0.06
    st
    0.06
    rire
    0.06
    Activations Density 0.103%

    No Known Activations