© 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. 25573
    Prev
    Next
    INDEX
    Explanations

    Drosophila

    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
    owoÅĽci
    -0.07
    urier
    -0.07
    Ñij
    -0.07
    uple
    -0.07
    ker
    -0.07
    roke
    -0.06
    åįı议书
    -0.06
    ãģªãģĵãģ¨
    -0.06
    dez
    -0.06
     Mercer
    -0.06
    POSITIVE LOGITS
    atika
    0.09
    çĪ±å¥½èĢħ
    0.07
     Trot
    0.07
    à¹Īาย
    0.07
    èĤ¡ä¸ľåıĬ
    0.07
    cide
    0.07
    rific
    0.07
    istica
    0.07
    egger
    0.07
    -fly
    0.06
    Activations Density 0.036%

    No Known Activations