© 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. 25517
    Prev
    Next
    INDEX
    Explanations

    instances counted

    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
     port
    -0.08
    åı¦è¡ĮéĢļçŁ¥
    -0.08
    omet
    -0.07
    ported
    -0.07
    rag
    -0.07
    dah
    -0.07
     zár
    -0.06
    ierer
    -0.06
    Ñģин
    -0.06
    .lex
    -0.06
    POSITIVE LOGITS
     counted
    0.19
     count
    0.18
     counting
    0.16
    Count
    0.16
    count
    0.16
     Count
    0.15
    计æķ°
    0.15
    _count
    0.14
    .Count
    0.13
     COUNT
    0.13
    Activations Density 0.104%

    No Known Activations