© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 746
    Prev
    Next
    INDEX
    Explanations

    say "car"

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

    No Comments

    Negative Logits
    XL
    -19.75
     XL
    -19.13
     MS
    -19.13
    畲
    -18.88
     JS
    -18.88
    tsx
    -18.13
     Oregon
    -18.00
    dart
    -18.00
    SSF
    -17.88
     الإسرائيل
    -17.88
    POSITIVE LOGITS
     CAR
    43.00
    CAR
    39.75
     Kar
    37.50
    Kar
    37.50
     Carlo
    32.75
    _CAR
    32.75
     kar
    32.50
     carb
    31.38
     Caroline
    31.38
    .Car
    30.75
    Activations Density 0.173%

    No Known Activations