© 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. 15085
    Prev
    Next
    INDEX
    Explanations

    columns of liquid or oil

    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
    åİ®
    -0.08
    æĹ©çĨŁ
    -0.08
    ilan
    -0.08
    åij½ä¸Ńçİĩ
    -0.08
    åŁŁ
    -0.07
    ivor
    -0.07
    akis
    -0.07
     serre
    -0.07
    åħľ
    -0.07
     rou
    -0.07
    POSITIVE LOGITS
     height
    0.08
    æĮĩ示
    0.07
     heights
    0.07
     measuring
    0.07
    height
    0.07
    读æķ°
    0.07
    æīĵåİĭ
    0.07
     Cân
    0.07
    é«ĺ度
    0.07
     cân
    0.07
    Activations Density 0.002%

    No Known Activations