© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 16364
    Prev
    Next
    INDEX
    Explanations

    say obedience

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    七星
    -20.00
     Lantern
    -19.25
    float
    -17.88
    芝加哥
    -17.25
    ,float
    -17.25
    .getFloat
    -17.00
    浮
    -16.88
    新华
    -16.88
     Fairfield
    -16.88
     Garland
    -16.88
    POSITIVE LOGITS
    SUB
    24.13
    服从
    24.00
    bsub
    23.00
     sub
    22.75
     obedience
    22.75
     SUB
    22.38
     Surre
    22.25
    臣
    22.00
     submissive
    22.00
     obed
    21.00
    Activations Density 0.361%

    No Known Activations