© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 168
    Prev
    Next
    INDEX
    Explanations

    say "ph"

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

    No Comments

    Negative Logits
    海淀区
    -24.00
    北京市
    -22.00
    海淀
    -21.38
    新京
    -19.88
     Brooklyn
    -19.75
     Greenwich
    -19.75
     kB
    -19.13
    Berlin
    -18.88
    在北京
    -18.75
    北京
    -18.13
    POSITIVE LOGITS
     PH
    60.50
     phosph
    58.00
    磷
    55.50
    PH
    53.25
     phosphate
    51.75
    PHP
    50.50
     PHP
    49.75
    磷酸
    49.75
    php
    48.25
     php
    48.00
    Activations Density 0.183%

    No Known Activations