© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15677
    Prev
    Next
    INDEX
    Explanations

    N/A

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

    No Comments

    Negative Logits
    4
    -52.75
     four
    -49.00
    四
    -43.50
     fourth
    -42.00
    四是
    -41.75
    four
    -41.50
     Fourth
    -40.75
     Four
    -39.75
    四个
    -39.75
    -four
    -39.00
    POSITIVE LOGITS
     Gust
    15.63
     reinst
    15.00
     Houses
    15.00
    _trip
    14.44
    ockey
    14.38
    口水
    14.38
    HOUSE
    14.25
    anking
    14.19
    ocking
    14.13
     redraw
    14.06
    Activations Density 0.758%

    No Known Activations