© 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. 16017
    Prev
    Next
    INDEX
    Explanations

    say non‑Latin characters

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

    No Comments

    Negative Logits
    -p
    -47.75
     getP
    -44.50
    PA
    -42.50
     PA
    -41.75
     PB
    -40.50
     pa
    -40.00
    pac
    -39.25
    -P
    -39.00
    帕
    -38.75
     PM
    -38.50
    POSITIVE LOGITS
    钏
    14.44
     Hoff
    14.44
    同盟
    13.88
    舸
    13.88
    桷
    13.56
    maf
    13.25
     Hermes
    13.13
    藁
    12.75
     liebe
    12.63
    狨
    12.31
    Activations Density 3.937%

    No Known Activations