© 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. 552
    Prev
    Next
    INDEX
    Explanations

    say "completion"

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

    No Comments

    Negative Logits
    茅
    -17.75
    ometers
    -17.38
     barn
    -17.25
    箔
    -16.75
    瓷
    -16.63
    醴
    -16.50
    钓
    -16.38
    打猎
    -16.13
    栅
    -16.13
    .radians
    -15.94
    POSITIVE LOGITS
    文
    18.50
     Bangkok
    17.13
    (text
    17.00
     text
    16.50
    _CHAT
    15.63
     SENT
    15.50
    Thai
    15.44
     Sent
    15.38
     Thai
    15.25
    (chat
    15.19
    Activations Density 0.030%

    No Known Activations