© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23154
    Prev
    Next
    INDEX
    Explanations

    variables ending in $

    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
    .GetEnumerator
    -0.07
    WindowState
    -0.07
    /*/
    -0.07
    .openg
    -0.06
    .gs
    -0.06
    åįĩåĪĿ
    -0.06
    æķĻäºİ
    -0.06
    μÏĢο
    -0.06
     inval
    -0.06
    æĽ´æĸ°äºİ
    -0.06
    POSITIVE LOGITS
    åħ³æ³¨åħ¬ä¼Ĺåı·
    0.07
    ricos
    0.07
    eon
    0.07
    çĦ¶åIJİæĬĬ
    0.07
    eyer
    0.07
     Devi
    0.07
    óri
    0.07
     trickle
    0.07
    सà¥įत
    0.07
    ern
    0.07
    Activations Density 0.011%

    No Known Activations