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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 16374
    Prev
    Next
    INDEX
    Explanations

    say "rotation"

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

    No Comments

    Negative Logits
    海滨
    -19.13
    _insn
    -17.25
    瑕
    -17.00
    iry
    -16.88
    Viet
    -16.75
    IPA
    -16.50
    汕
    -16.50
    沿海
    -16.38
    aland
    -16.25
    ogo
    -16.25
    POSITIVE LOGITS
     rotor
    23.25
    旋转
    22.75
    (rotation
    22.75
     rotates
    22.00
     Rotation
    21.88
    _ROT
    21.63
    ROT
    21.50
     rotational
    21.50
     rotation
    21.50
     rot
    21.50
    Activations Density 0.890%

    No Known Activations