© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 850
    Prev
    Next
    INDEX
    Explanations

    say "butterfly"

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

    No Comments

    Negative Logits
     RS
    -22.00
    _rs
    -20.00
    แร
    -18.13
    _RS
    -17.50
    /rs
    -17.25
     XS
    -17.00
    芜湖
    -17.00
     Rak
    -16.88
    磴
    -16.88
     miners
    -16.75
    POSITIVE LOGITS
     Butterfly
    37.25
     Butter
    36.50
     butterfly
    35.50
    蝴蝶
    32.75
    .Butter
    32.75
     butter
    31.25
    蝶
    30.75
     butterflies
    30.75
    flies
    26.75
    fly
    25.50
    Activations Density 0.043%

    No Known Activations