© 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. 15741
    Prev
    Next
    INDEX
    Explanations

    say "p" tokens

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

    No Comments

    Negative Logits
    钏
    -15.19
     Hoff
    -14.81
    maf
    -14.56
    同盟
    -13.88
    桷
    -13.75
     Hermes
    -13.69
    舸
    -13.56
    狨
    -13.25
    藁
    -13.13
    鞑
    -13.06
    POSITIVE LOGITS
    -p
    47.50
     getP
    44.50
    PA
    41.50
     PA
    41.00
     PB
    40.00
     pa
    39.00
    PB
    38.50
    -P
    38.25
    /p
    38.00
    pb
    38.00
    Activations Density 7.856%

    No Known Activations