© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20599
    Prev
    Next
    INDEX
    Explanations

    Indian High Commissioner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gag
    -0.06
    নি
    -0.05
    é½IJåħ¨
    -0.05
    wall
    -0.05
    èĽ¾
    -0.05
    uzzle
    -0.05
    елÑĮ
    -0.05
     акаде
    -0.05
    odial
    -0.05
    æĺ¯ç¬¬ä¸Ģ
    -0.05
    POSITIVE LOGITS
    ÅĻe
    0.06
    ikai
    0.06
     nex
    0.05
    кÑĢи
    0.05
     manti
    0.05
    æ¯ıä¸Ģ项
    0.05
    orden
    0.05
    å½ķ
    0.05
    jist
    0.05
    liga
    0.05
    Activations Density 0.001%

    No Known Activations