© 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. 25676
    Prev
    Next
    INDEX
    Explanations

    compound phrases

    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
    à¸ĺรรมà¸Ĭาà¸ķิà¹ģละ
    -0.13
    å°ĬéĩįåĴĮ
    -0.12
    èµĦæĸĻåĴĮ
    -0.11
    交æµģåĴĮ
    -0.10
    çī¹èī²åĴĮ
    -0.10
    éĶĻ误æĪĸ
    -0.10
    à¹ģละมี
    -0.10
    ç»ıéªĮåĴĮ
    -0.10
    æĪIJéķ¿åĴĮ
    -0.10
    稳å®ļåĴĮ
    -0.10
    POSITIVE LOGITS
     alike
    0.15
    /or
    0.12
     thereof
    0.12
    åĽ¾çŃī
    0.11
     sebagainya
    0.11
    å·¥ç¨ĭçŃī
    0.10
     lainnya
    0.10
     sowie
    0.10
     therein
    0.10
    管çIJĨçŃī
    0.10
    Activations Density 0.542%

    No Known Activations