© 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. 102
    Prev
    Next
    INDEX
    Explanations

    say "math"

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

    No Comments

    Negative Logits
    deer
    -21.50
     Monsanto
    -19.88
    产销
    -18.63
     PCS
    -18.38
     molec
    -18.25
     Lup
    -18.25
     LR
    -18.00
     welding
    -17.88
    _LS
    -17.88
    _LCD
    -17.75
    POSITIVE LOGITS
    数学
    28.63
     mathematic
    28.38
     mathematics
    26.00
     Mathematics
    22.75
     mathematical
    22.25
     math
    21.63
     Mathematic
    21.50
    (math
    21.13
     Mathematical
    20.75
    math
    20.50
    Activations Density 0.135%

    No Known Activations