© 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
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 15932
    Prev
    Next
    INDEX
    Explanations

    say "water"

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

    No Comments

    Negative Logits
    旋转
    -17.63
    母
    -17.38
     Cornel
    -17.13
    角
    -17.00
     rotates
    -16.88
     angles
    -16.75
    -cat
    -16.75
     rotations
    -16.63
    .python
    -16.50
     Matthias
    -16.38
    POSITIVE LOGITS
    sea
    20.75
     Sea
    20.50
    Sea
    20.38
     sea
    20.25
    瀑布
    19.75
     Bounty
    19.63
    礁
    19.50
     Reef
    19.25
     oasis
    19.00
    墟
    19.00
    Activations Density 0.973%

    No Known Activations