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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 16169
    Prev
    Next
    INDEX
    Explanations

    say "baptism"

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

    No Comments

    Negative Logits
    评价
    -19.63
    visor
    -18.75
     evaluates
    -18.38
    eval
    -17.50
     evaluator
    -17.38
     evaluate
    -17.13
    _QMARK
    -16.50
    _eval
    -16.50
     eval
    -16.25
     evaluated
    -16.13
    POSITIVE LOGITS
     bapt
    25.50
     baptism
    25.25
     Bapt
    24.00
     baptized
    22.38
    洗净
    22.25
    澡
    22.13
    洗礼
    21.75
     water
    20.88
    洗
    20.63
    水
    20.50
    Activations Density 0.135%

    No Known Activations