© 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. 23250
    Prev
    Next
    INDEX
    Explanations

    examples and specific cases

    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
    è·Ł
    -0.06
     Isl
    -0.06
    ä¹Łå°±æĺ¯
    -0.06
    ä¼¼ä¹İ
    -0.06
    _MISC
    -0.06
    ...
    -0.06
    å¾Ģ
    -0.06
    inou
    -0.05
    ↵
    -0.05
     self
    -0.05
    POSITIVE LOGITS
    ä¹ĭäºİ
    0.12
    åıĪå¦Ĥ
    0.11
    å°±æĽ¾
    0.10
    çĤºä¾ĭ
    0.10
    æ´»åĬ¨çŃī
    0.10
     à¹Ģà¸Ľà¹ĩà¸Ļà¸ķà¹īà¸Ļ
    0.09
    æĥħåĨµçŃī
    0.09
    å°±æĺ¯ä¸ª
    0.09
    å°±å¾Ī
    0.09
    å°±æĺ¯ä¸Ģ个
    0.09
    Activations Density 0.099%

    No Known Activations