© 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. 19516
    Prev
    Next
    INDEX
    Explanations

    combustion engine

    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
    å°¤
    -0.07
    çĸ¯
    -0.07
     Massa
    -0.06
    个åİ¿
    -0.06
    忧
    -0.05
    åľĥ
    -0.05
     gord
    -0.05
    çħ¦
    -0.05
    dur
    -0.05
    |RF
    -0.05
    POSITIVE LOGITS
    enville
    0.09
    buk
    0.08
    æīĭæľºç«Ļ
    0.08
    çĻ¾ç§ijåħ¨ä¹¦
    0.08
    ây
    0.08
    aho
    0.08
    ĶĦ
    0.07
    ächt
    0.07
    cia
    0.07
     asian
    0.07
    Activations Density 0.043%

    No Known Activations