© 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. 20869
    Prev
    Next
    INDEX
    Explanations

    filenames with `.txt` extension

    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
    ç´Ĺ
    -0.06
    pas
    -0.06
    çķ´
    -0.06
    ä»ĩ
    -0.06
    纱
    -0.06
    ä¸įç»Ŀ
    -0.06
    alf
    -0.06
    jut
    -0.06
    岸
    -0.06
     Dunn
    -0.06
    POSITIVE LOGITS
    æĶ¾åľ¨äºĨ
    0.07
     Whip
    0.07
    åľ¨åIJij
    0.07
    zków
    0.07
    æĹ¥èµ·
    0.07
    abouts
    0.07
    }->
    0.07
    çłĶä¿®
    0.07
    بÙĤ
    0.07
    éĻ¤ä»¥
    0.07
    Activations Density 0.001%

    No Known Activations