© 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. 47703
    Prev
    Next
    INDEX
    Explanations

    before

    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
    åįĬéĢĶ
    -0.08
     Metr
    -0.07
    /thumb
    -0.07
     à¸Ńà¹Īาà¸Ļà¸ķà¹Īà¸Ń
    -0.07
     Postado
    -0.07
    upo
    -0.07
     Thrones
    -0.07
    athan
    -0.07
    æĬķèµĦäºĭ件
    -0.07
    .Option
    -0.06
    POSITIVE LOGITS
    好åķ¦
    0.08
     chân
    0.08
    ieÅĦ
    0.07
    é»ĺé»ĺçļĦ
    0.07
    ellos
    0.07
    çļĦæľīåħ³è§Ħå®ļ
    0.07
    [test
    0.07
    åij¨è¾¹çݯå¢ĥ
    0.07
    vio
    0.06
    æĽ´å¥½çļĦèĩªå·±
    0.06
    Activations Density 0.809%

    No Known Activations