© 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. 49848
    Prev
    Next
    INDEX
    Explanations

    eye contact

    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
    unes
    -0.08
    shr
    -0.08
    èĢ³è¾¹
    -0.07
    æĽ´æĸ°æĹ¥æľŁ
    -0.07
    kle
    -0.07
    æīĭ头
    -0.07
    пло
    -0.07
    جار
    -0.07
    åĸľéĹ»
    -0.07
    uari
    -0.07
    POSITIVE LOGITS
    çľ¼ç¥ŀ
    0.14
    çļĦçľ¼ç¥ŀ
    0.12
    çļĦ缮åħī
    0.12
     gaze
    0.12
    注è§Ĩ
    0.12
    缮åħī
    0.11
    缴è§Ĩ
    0.11
    çŀ³åŃĶ
    0.11
     stare
    0.11
    çļĦçľ¼çĿĽ
    0.11
    Activations Density 0.051%

    No Known Activations