© 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. 38462
    Prev
    Next
    INDEX
    Explanations

    us to

    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
    اÙĭ
    -0.10
    ÅĽci
    -0.09
    eur
    -0.09
    Ùĭ
    -0.08
    mente
    -0.08
    ive
    -0.08
    itude
    -0.07
    ingg
    -0.07
    ly
    -0.07
    ãģ³
    -0.07
    POSITIVE LOGITS
    /her
    0.12
    /us
    0.11
     mesmos
    0.11
     mismos
    0.11
    -même
    0.10
    zelf
    0.10
     stessi
    0.09
     οÏĢοί
    0.09
    å©¿
    0.09
    eland
    0.09
    Activations Density 0.136%

    No Known Activations