© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2611
    Prev
    Next
    INDEX
    Explanations

    say "顾"

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

    No Comments

    Negative Logits
    [res
    -19.25
     Morph
    -17.50
    Simulation
    -17.38
    simulation
    -17.13
    sem
    -17.13
     Mel
    -16.75
     meth
    -16.63
    甲
    -16.63
    (sim
    -16.63
     simulation
    -16.50
    POSITIVE LOGITS
    顾
    70.50
    Cons
    60.00
     Cons
    60.00
    顧
    58.50
    cons
    57.50
     cons
    57.00
    -cons
    52.75
    .cons
    49.75
     CONS
    49.75
    _cons
    48.00
    Activations Density 0.032%

    No Known Activations