© 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. 17834
    Prev
    Next
    INDEX
    Explanations

    code snippet suffixes

    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
    witz
    -0.08
    ạp
    -0.08
    chy
    -0.08
    ĺ
    -0.08
    åĨįåĬłä¸Ĭ
    -0.07
    ampf
    -0.07
    εÏħ
    -0.07
    ulet
    -0.07
    .TryParse
    -0.07
    ุà¸ģ
    -0.07
    POSITIVE LOGITS
    没ä»Ģä¹Ī
    0.08
     Roos
    0.07
    ä¹Łæ²¡ä»Ģä¹Ī
    0.07
     mentioned
    0.07
    ä¸įä¸Ģ
    0.07
    ä¹Łæ²¡æľīä»Ģä¹Ī
    0.06
     involved
    0.06
    istere
    0.06
    èĽĽ
    0.06
     propri
    0.06
    Activations Density 0.123%

    No Known Activations