© 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. 47984
    Prev
    Next
    INDEX
    Explanations

    what to do

    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
    èĩªè¡ĮæıIJä¾Ľ
    -0.08
    æĹłæĦıä¸Ń
    -0.07
     Opp
    -0.07
    å¦ĤæĦ¿
    -0.06
     accidentally
    -0.06
    åĽŀ羸
    -0.06
    表达èĥ½åĬĽ
    -0.06
     ghép
    -0.06
    åģ¶çĦ¶
    -0.06
     previews
    -0.06
    POSITIVE LOGITS
    åºĶç«ĭåį³
    0.13
    çļĦ第ä¸ĢæŃ¥
    0.13
     immediate
    0.12
    第ä¸ĢæŃ¥
    0.12
    Immediate
    0.12
     immédi
    0.12
     немед
    0.12
     immediately
    0.11
    ç«ĭåį³
    0.11
    ä¸ĭä¸ĢæŃ¥
    0.11
    Activations Density 0.065%

    No Known Activations