© 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. 2149
    Prev
    Next
    INDEX
    Explanations

    say mir

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

    No Comments

    Negative Logits
    den
    -19.75
    玻璃
    -18.75
    segment
    -18.75
     segment
    -17.38
     consenting
    -16.50
     glass
    -16.38
    刻
    -16.38
     Denis
    -15.69
    glass
    -15.63
    Glass
    -15.44
    POSITIVE LOGITS
    Mir
    57.00
     Mir
    56.25
     mir
    48.25
    mir
    43.00
     mirrored
    32.75
     Miranda
    31.38
     reflected
    31.25
     reflect
    31.00
     Reflect
    30.63
     reflecting
    29.50
    Activations Density 0.032%

    No Known Activations