© 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. 13
    Prev
    Next
    INDEX
    Explanations

    [from] => [from]

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

    No Comments

    Negative Logits
    .wp
    -22.50
     bb
    -21.50
    WP
    -21.25
     GG
    -20.75
    湖区
    -19.75
     WP
    -19.25
    皖
    -19.13
    泰州
    -19.00
     OO
    -19.00
     BB
    -19.00
    POSITIVE LOGITS
     DM
    25.88
    _fm
    23.88
     FM
    22.88
     fm
    22.88
     FR
    22.88
     dm
    22.38
     FD
    21.63
    .fm
    21.38
     DR
    21.25
    dm
    20.63
    Activations Density 0.578%

    No Known Activations