© 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. 64653
    Prev
    Next
    INDEX
    Explanations

    Satan, Lucifer, demon, devil

    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
    è¿Ļ两款
    -0.07
     بÙħد
    -0.07
    mara
    -0.07
    lien
    -0.07
    ewater
    -0.07
    å¿ĺä¸įäºĨ
    -0.07
    रण
    -0.07
    åľ°éĽ·
    -0.07
    غاÙħ
    -0.07
    è±Į
    -0.07
    POSITIVE LOGITS
     Satan
    0.10
     tempt
    0.09
     tempting
    0.09
     Lucifer
    0.09
    常驻
    0.08
    路西
    0.08
     temptation
    0.08
    ibaba
    0.08
    tempt
    0.08
    oven
    0.08
    Activations Density 0.036%

    No Known Activations