© 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. 1638
    Prev
    Next
    INDEX
    Explanations

    Arabic names and Islamic terms

    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
    viv
    -0.07
    èĩªçĦ¶ä¹Ł
    -0.07
    æµıè§Ī次æķ°
    -0.06
    æĥ¨éģŃ
    -0.06
    oard
    -0.06
    æ§Ľ
    -0.06
    æĪIJèį¯
    -0.06
     Kund
    -0.06
    rzy
    -0.06
    вив
    -0.06
    POSITIVE LOGITS
    lems
    0.07
    uet
    0.07
     ìĤ°
    0.07
     اÙĦØ´ÙĬ
    0.06
    liness
    0.06
    æ¯Ĥ
    0.06
    mans
    0.06
    ography
    0.06
    dde
    0.06
    qt
    0.06
    Activations Density 0.009%

    No Known Activations