© 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. 46039
    Prev
    Next
    INDEX
    Explanations

    reflect on what

    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
    åģļ为
    -0.08
    åIJİæľī
    -0.07
    .toDouble
    -0.07
    èIJ¨å°Ķ
    -0.07
    egis
    -0.07
    aih
    -0.07
    Ø·Ùģ
    -0.07
    eding
    -0.07
    æĥŁæľī
    -0.06
    Ñĸй
    -0.06
    POSITIVE LOGITS
    åħ³äºİåĬłå¼º
    0.07
    çĬ
    0.07
    ":"+
    0.07
     überhaupt
    0.06
    Cold
    0.06
    èģ
    0.06
    inds
    0.06
    à¸ļà¹īาà¸ĩ
    0.06
     relevant
    0.06
     Trem
    0.06
    Activations Density 0.002%

    No Known Activations