© 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. 2076
    Prev
    Next
    INDEX
    Explanations

    say "visit" words

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

    No Comments

    Negative Logits
    eros
    -17.50
     regulator
    -17.13
     regulators
    -16.63
    ert
    -15.50
    abble
    -15.00
    直升机
    -14.44
     poles
    -14.38
     erm
    -14.38
    asher
    -14.25
    erdem
    -14.25
    POSITIVE LOGITS
     visit
    69.00
     visitor
    67.50
     visits
    64.00
    Vis
    63.00
    .vis
    62.75
    (vis
    62.75
    visit
    62.50
     visited
    62.25
     Vis
    62.00
     visitors
    61.25
    Activations Density 0.207%

    No Known Activations