© 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. 18555
    Prev
    Next
    INDEX
    Explanations

    touch screen, display, apparatus

    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
    andia
    -0.08
    cia
    -0.08
    å®ĺæĸ¹åįļ客
    -0.07
    amal
    -0.07
    acci
    -0.07
    iglia
    -0.07
    è®©æĽ´å¤ļ读èĢħ
    -0.07
    lesh
    -0.07
    cier
    -0.07
    epass
    -0.07
    POSITIVE LOGITS
     Huawei
    0.07
    æľīçĽĬ
    0.07
    loh
    0.07
     Ting
    0.07
     Dong
    0.07
    Hu
    0.06
     Timo
    0.06
    æĶ¶èİ·äºĨ
    0.06
    æ¾ľ
    0.06
    vision
    0.06
    Activations Density 0.127%

    No Known Activations