© 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. 1041
    Prev
    Next
    INDEX
    Explanations

    suffixes like -oid, -osis, -ography, -itis, -etros

    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
    ủng
    -0.07
    æĺ¯å¯¼èĩ´
    -0.07
    unken
    -0.07
     sacco
    -0.07
    åħ«æľĪ
    -0.07
    rine
    -0.07
    ç±»çŃī
    -0.07
     ÙĪباÙĦتاÙĦÙĬ
    -0.07
    ential
    -0.07
    клей
    -0.07
    POSITIVE LOGITS
    ä¹Łåı«
    0.07
    注éĩį
    0.07
    ä¹į
    0.07
    æĽ´æ³¨éĩį
    0.07
    æ³ĽæĮĩ
    0.07
    æĺ¯æĮĩåľ¨
    0.07
    avat
    0.07
    hell
    0.07
     mÉĻrc
    0.06
    orst
    0.06
    Activations Density 0.049%

    No Known Activations