© 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. 2785
    Prev
    Next
    INDEX
    Explanations

    say "_{"

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

    No Comments

    Negative Logits
     REG
    -20.88
    REG
    -20.75
    Mir
    -19.38
    (REG
    -19.25
     Registry
    -19.25
    reg
    -19.25
    ver
    -17.88
    Gem
    -17.25
    咨询
    -16.75
    register
    -16.63
    POSITIVE LOGITS
    _{
    36.25
     leg
    27.00
     Leg
    26.25
    ^{
    25.38
    Leg
    24.63
    _leg
    22.88
     legs
    21.88
    leg
    21.63
    }_{
    21.63
     Legs
    20.13
    Activations Density 0.013%

    No Known Activations