© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39793
    Prev
    Next
    INDEX
    Explanations

    Greek letters and endings

    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
    _WATCH
    -0.08
    umph
    -0.07
    为æŃ¢
    -0.07
    èĩ¨
    -0.07
    çĶĺ
    -0.07
    临
    -0.07
    Ùħاس
    -0.07
    è¿ĺæľīå¾Īå¤ļ
    -0.07
     })).
    -0.06
    æł¼å¼ıçļĦ
    -0.06
    POSITIVE LOGITS
     cuy
    0.08
    atab
    0.08
    å¸ĥä»Ģ
    0.07
    aki
    0.07
    apr
    0.07
    evin
    0.07
     cuyos
    0.07
    _CA
    0.07
    å°±æĺ¯æĬĬ
    0.07
    åľ¨åŃ¦ä¹łä¸Ĭ
    0.07
    Activations Density 0.065%

    No Known Activations