© 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. 46678
    Prev
    Next
    INDEX
    Explanations

    all or entire

    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
    é«ĺ人
    -0.08
    Ø·ÙĦ
    -0.07
    缴æݥ使çĶ¨
    -0.07
    æĪĸèĢħ缴æİ¥
    -0.07
    éĢī人
    -0.07
     spok
    -0.07
    è§Ħå®ļçļĦåħ¶ä»ĸ
    -0.07
    ape
    -0.07
    ÑĨеп
    -0.07
    uning
    -0.07
    POSITIVE LOGITS
    åħ¨éĥ¨çļĦ
    0.13
     تÙĤرÙĬب
    0.13
    åħ¨éĥ¨
    0.12
    æĪĸéĥ¨åĪĨ
    0.11
    çļĦåħ¨éĥ¨
    0.10
    à¸Ĺัà¹īà¸ĩหมà¸Ķ
    0.10
    æīĢæľīçļĦ
    0.09
     entire
    0.09
    æĤīæķ°
    0.09
     habis
    0.09
    Activations Density 0.060%

    No Known Activations