© 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. 47049
    Prev
    Next
    INDEX
    Explanations

    surprising not present

    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
    æł©
    -0.08
    доÑĢ
    -0.08
    gad
    -0.08
    dür
    -0.07
    æĹłæĦı
    -0.07
    éĽ¯
    -0.07
    agas
    -0.07
    ģ
    -0.07
    æĸ°åŃ¦æľŁ
    -0.07
    欢è¿İéĺħ读
    -0.07
    POSITIVE LOGITS
     hätte
    0.10
    æľĢèµ·çłģ
    0.09
    æīį对
    0.09
    åºĶæľīçļĦ
    0.09
    ãĤĤãģĨå°ijãģĹ
    0.09
    åı¯æĥľ
    0.09
    éĥ½åºĶ该
    0.09
     wären
    0.09
    èµ·çłģ
    0.09
    åºĶ该æľī
    0.09
    Activations Density 0.493%

    No Known Activations