© 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. 16094
    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
    卧
    -18.50
    -basket
    -16.88
    (sigma
    -16.13
     sigma
    -15.25
    sigma
    -15.19
     santa
    -15.00
     sud
    -15.00
    寝
    -14.81
    券
    -14.25
    睡
    -14.13
    POSITIVE LOGITS
     ph
    74.00
     Ph
    73.50
    Ph
    73.00
    ph
    73.00
    -ph
    69.50
    (ph
    68.50
    _ph
    67.50
    /ph
    65.50
     PH
    65.00
    .ph
    64.50
    Activations Density 0.339%

    No Known Activations