© 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. 61113
    Prev
    Next
    INDEX
    Explanations

    Islamic religious 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
    ylv
    -0.07
    硬
    -0.06
     flatt
    -0.06
     Appalachian
    -0.06
     RTE
    -0.06
    èĥĥåı£
    -0.06
    婪
    -0.06
    äch
    -0.06
     luckily
    -0.06
    ritz
    -0.06
    POSITIVE LOGITS
     Quran
    0.10
    hud
    0.09
     Qur
    0.09
     Ibn
    0.09
    æ¸ħ羣
    0.08
    -bin
    0.08
    Hu
    0.08
     Medina
    0.08
    OBJ
    0.08
    éªĨ驼
    0.08
    Activations Density 0.060%

    No Known Activations