© 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. 46331
    Prev
    Next
    INDEX
    Explanations

    generally nasty weather

    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
    oot
    -0.08
    æĿı
    -0.07
    igin
    -0.07
    _COD
    -0.07
    ç£ĭ
    -0.07
    ooter
    -0.07
    åı¤éģĵ
    -0.07
    uku
    -0.06
    åķĦ
    -0.06
    éĤ£åıĮ
    -0.06
    POSITIVE LOGITS
     insomma
    0.15
    è¿Ļä¸ĢåĪĩ
    0.12
    è¿ĻäºĽéĥ½
    0.12
    è¿ĻäºĽéĥ½æĺ¯
    0.11
    æĢ»ä¹ĭ
    0.10
    è¿ĻäºĽåĽłç´ł
    0.10
    è¿Ļéĥ½æĺ¯
    0.10
    æīĢæľīè¿ĻäºĽ
    0.09
     altogether
    0.09
    æĢ»èĢĮè¨Ģä¹ĭ
    0.08
    Activations Density 0.745%

    No Known Activations