© 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. 56641
    Prev
    Next
    INDEX
    Explanations

    Muslim or Islam related phrases

    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
     Druid
    -0.09
     EDUCA
    -0.09
     Lyme
    -0.08
    jax
    -0.08
     ukrain
    -0.08
    æ³°åĿ¦
    -0.08
    åį°ç¬¬å®ī
    -0.08
     Slovakia
    -0.07
     Ukrain
    -0.07
    éĤij
    -0.07
    POSITIVE LOGITS
     Sheikh
    0.12
    ä¼Ĭæĸ¯åħ°
    0.10
     Ibrahim
    0.09
     Arabic
    0.09
     Islamic
    0.09
     Ibn
    0.09
     Khan
    0.09
    æ¸ħ羣
    0.09
     Q
    0.09
    ķĮ
    0.09
    Activations Density 0.754%

    No Known Activations