© 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. 8306
    Prev
    Next
    INDEX
    Explanations

    closest to

    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
    /testing
    -0.08
    é¢ĩå¤ļ
    -0.08
    å·®ä¸įå¤ļäºĨ
    -0.08
    ieger
    -0.08
    ÙģÙĬÙĩ
    -0.08
     eigentlich
    -0.08
    ilt
    -0.08
    确认åIJİ
    -0.08
    sst
    -0.08
    ä¹ĭå¤ļ
    -0.08
    POSITIVE LOGITS
    åĴĮæľĢ
    0.10
    ä¹Łæĺ¯æľĢ
    0.08
    åħ¨æĸĩ
    0.07
    çĪĨæ£ļ
    0.06
     unde
    0.06
    çīĪæĿĥ声æĺİ
    0.06
    åħ¶æ¬¡æĺ¯
    0.06
    est
    0.06
    ä¹ŁæĽ´
    0.06
     than
    0.06
    Activations Density 0.020%

    No Known Activations