© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14083
    Prev
    Next
    INDEX
    Explanations

    say "brain"

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

    No Comments

    Negative Logits
     exporters
    -20.25
     export
    -19.50
     exporter
    -19.13
     Export
    -18.13
    .Export
    -17.75
    .export
    -17.38
    -export
    -17.38
    export
    -17.00
    uard
    -16.75
     exported
    -16.75
    POSITIVE LOGITS
    脑
    34.75
     brain
    34.75
    brain
    31.25
    大脑
    31.25
     brains
    31.00
    Brain
    30.88
     Brain
    29.88
    腦
    27.50
    brains
    27.00
    Brains
    25.63
    Activations Density 0.659%

    No Known Activations