© 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. 64982
    Prev
    Next
    INDEX
    Explanations

    reload or update

    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
    subpackage
    -0.08
    Ỽt
    -0.07
    egade
    -0.07
    alas
    -0.07
     hopefully
    -0.07
     neither
    -0.07
    dden
    -0.06
    ÙĪرت
    -0.06
     __________________________________
    -0.06
    æĺĵè´Ń
    -0.06
    POSITIVE LOGITS
    è¿Ļä¹Īç®Ģåįķ
    0.11
    éĤ£ä¹Īç®Ģåįķ
    0.11
    èĢĮæĺ¯
    0.10
    èĢĮæĺ¯åĽłä¸º
    0.09
    å°±ä¸Ģå®ļ
    0.09
    èĢĮæĺ¯åľ¨
    0.08
    èĢĮæĺ¯è¦ģ
    0.08
    ç«ĭåį³
    0.08
    _VO
    0.08
    è¿Ļä¹Īå¿«
    0.07
    Activations Density 0.030%

    No Known Activations