© 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. 19897
    Prev
    Next
    INDEX
    Explanations

    product descriptions and features

    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
    idik
    -0.07
    å°½æĺ¯
    -0.06
     intric
    -0.06
    .tom
    -0.06
    ãģ©ãģĵãĤį
    -0.06
     ×ĸ×ķ
    -0.06
    ä¹Łå°±æĺ¯
    -0.06
    orni
    -0.06
    ÙĦاء
    -0.06
    è¿ĩä¸Ĭ
    -0.06
    POSITIVE LOGITS
     вза
    0.08
    CEL
    0.07
    REE
    0.07
    (PC
    0.07
    gc
    0.07
     Minta
    0.07
     kund
    0.07
    bbc
    0.07
     câte
    0.07
    unities
    0.07
    Activations Density 0.612%

    No Known Activations