© 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. 64560
    Prev
    Next
    INDEX
    Explanations

    network location or context

    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
    ç¡®
    -0.09
    æĽ¼
    -0.07
    om
    -0.06
    åį«åĽ½
    -0.06
    Ñĥк
    -0.06
    åıĪéģĵ
    -0.06
    èĩªå·±çļĦ人
    -0.06
    eras
    -0.06
     bef
    -0.06
    ste
    -0.06
    POSITIVE LOGITS
     aka
    0.08
    exercice
    0.07
    ä¿Ĺ称
    0.07
    ç»ıè¿ĩäºĨ
    0.07
    çŃ¾å®ļ
    0.07
    arel
    0.07
    ottie
    0.07
     yani
    0.07
    åıĪ称为
    0.07
    ingleton
    0.06
    Activations Density 0.133%

    No Known Activations