© 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. 12382
    Prev
    Next
    INDEX
    Explanations

    Arabic words and 'control'/'civil'

    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
     s
    -0.06
     pro
    -0.06
    zez
    -0.05
    çĶŁ
    -0.05
     deb
    -0.05
    ,
    -0.05
     of
    -0.05
    arend
    -0.05
     instrument
    -0.05
    åį°
    -0.05
    POSITIVE LOGITS
    å¾·åįİ
    0.09
    åĬłæĭ¿å¤§çļĦ
    0.09
    epsi
    0.09
    usra
    0.09
     fabr
    0.08
    клад
    0.08
    对åħ¶çľŁå®ŀæĢ§è´Łè´£
    0.08
    gris
    0.08
    ökk
    0.08
    -Cs
    0.08
    Activations Density 0.007%

    No Known Activations