© 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. 1069
    Prev
    Next
    INDEX
    Explanations

    http:// URLs

    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
    unga
    -0.08
    irc
    -0.07
    åIJįåŃĹåı«
    -0.07
    lish
    -0.07
    XI
    -0.07
    isi
    -0.07
    mers
    -0.07
    irk
    -0.07
    XC
    -0.07
    dev
    -0.07
    POSITIVE LOGITS
    ä»»çĶ±
    0.07
    åĪ°èĢģ
    0.07
    ç½Ħ
    0.07
    é»ijè±Ĩ
    0.06
    æľŁæ»¡
    0.06
    å±ħé«ĺ
    0.06
    åĪĨå·¦åı³
    0.06
     Äĩ
    0.06
     Hanson
    0.06
    æĿĥåĴĮ
    0.06
    Activations Density 0.003%

    No Known Activations