© 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. 39058
    Prev
    Next
    INDEX
    Explanations

    God, Jesus, spiritual

    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
    opin
    -0.07
     evolve
    -0.07
    ç²ĭ
    -0.06
    åĭĩå¾Ģ缴åīį
    -0.06
    æ¼Ķ
    -0.06
     unlucky
    -0.06
    天涯
    -0.06
    çĤ¸
    -0.06
    ideographic
    -0.06
    à¸Ī
    -0.06
    POSITIVE LOGITS
    åĸľä¹IJ
    0.11
     Scripture
    0.10
     fellowship
    0.10
     covenant
    0.10
     Psalm
    0.10
    Script
    0.10
     Script
    0.09
     Eph
    0.09
     spiritual
    0.09
     Gospel
    0.09
    Activations Density 0.351%

    No Known Activations