© 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. 2015
    Prev
    Next
    INDEX
    Explanations

    Purana, green tea, new version

    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
    रà¥įफ
    -0.09
    azin
    -0.08
     Cristal
    -0.08
    ç«¥è¯Ŀ
    -0.07
    åijĽ
    -0.07
     franc
    -0.07
    emie
    -0.07
    aix
    -0.07
     Crystal
    -0.07
    æİĸ
    -0.07
    POSITIVE LOGITS
     Saras
    0.10
     Bhar
    0.10
     Uttar
    0.10
     Brah
    0.10
    åį°åº¦
    0.10
     Vish
    0.09
     Bihar
    0.09
     Gujarat
    0.08
     ÅĽ
    0.08
     Karnataka
    0.08
    Activations Density 0.078%

    No Known Activations