© 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. 24142
    Prev
    Next
    INDEX
    Explanations

    imaging revealed contrast enhancement / wing aircraft

    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
    èĬ±èĬ±
    -0.07
    ç«ĭåį³è´Ńä¹°
    -0.07
    olland
    -0.06
    ÄįiÄĩ
    -0.06
    æĺ¯æĪijåĽ½
    -0.06
    zwischen
    -0.06
    cina
    -0.06
    WithContext
    -0.06
    ssen
    -0.06
    çīĪçļĦ
    -0.06
    POSITIVE LOGITS
    å¦Ĥçİī
    0.09
     devices
    0.08
    æ©Łéĸ¢
    0.08
    çī¹åĪ«æĺ¯
    0.08
     вÑĢоде
    0.08
     berupa
    0.08
     ÑĤипа
    0.08
    ï¼Ī
    0.08
     ÙĥاÙĦ
    0.08
    formen
    0.07
    Activations Density 1.345%

    No Known Activations