© 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. 60309
    Prev
    Next
    INDEX
    Explanations

    loyalty and treason

    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
    OrNil
    -0.07
    reater
    -0.07
    zó
    -0.07
    Ø´ÙĨا
    -0.07
    èį¤
    -0.06
    oul
    -0.06
     شدÙĨ
    -0.06
    ierer
    -0.06
    çĶ±è¢«åijĬ
    -0.06
    tures
    -0.06
    POSITIVE LOGITS
    èģĮå®Ī
    0.12
    loy
    0.11
    å¿łè¯ļ
    0.11
     loyalty
    0.10
    alty
    0.10
    LOY
    0.09
    å¿łäºİ
    0.09
    å¿łå¿ĥ
    0.09
     Loy
    0.09
     envers
    0.09
    Activations Density 0.024%

    No Known Activations