© 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. 14208
    Prev
    Next
    INDEX
    Explanations

    say "installation"

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

    No Comments

    Negative Logits
    榔
    -16.25
    .qq
    -15.94
     grenade
    -15.81
    igrant
    -15.63
     BN
    -15.50
    FML
    -15.38
    唧
    -15.31
     getService
    -15.19
    iqu
    -15.13
    ademic
    -14.94
    POSITIVE LOGITS
     installation
    31.25
    安装
    30.63
     installations
    28.00
     install
    27.63
    -install
    27.63
     panels
    26.88
     Panels
    26.38
    panels
    26.38
     Installation
    26.00
     installs
    25.88
    Activations Density 0.197%

    No Known Activations