© 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. 42849
    Prev
    Next
    INDEX
    Explanations

    who joined Roman military

    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
    åݦ
    -0.07
    ä¹ĥèĩ³
    -0.06
    immer
    -0.06
    åįĬ
    -0.06
    æĪijåı«
    -0.06
     Lie
    -0.06
    errer
    -0.06
    以大
    -0.06
    Man
    -0.06
     Manz
    -0.06
    POSITIVE LOGITS
    Mixin
    0.08
    ecessarily
    0.08
    criptor
    0.08
    ajara
    0.07
    hoek
    0.07
    ROKE
    0.07
    QObject
    0.07
    utex
    0.07
     whoever
    0.07
    noon
    0.07
    Activations Density 0.001%

    No Known Activations