© 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
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15581
    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
     contracting
    -16.00
    ellan
    -16.00
    QUOTE
    -15.81
    xDD
    -15.75
    xAB
    -15.31
     confinement
    -15.19
     contracted
    -15.13
    summ
    -15.00
     trusts
    -14.94
    _COMPILER
    -14.88
    POSITIVE LOGITS
     pH
    18.50
     PH
    17.75
    _ph
    16.88
    (ph
    16.38
     readings
    16.38
     range
    16.25
     Ph
    15.81
     pBuffer
    15.81
    _PH
    15.69
     ph
    15.44
    Activations Density 0.067%

    No Known Activations