© 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. 680
    Prev
    Next
    INDEX
    Explanations

    say yellow

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

    No Comments

    Negative Logits
    .pg
    -19.75
     Gos
    -17.38
     PostgreSQL
    -17.25
    rove
    -17.00
     rc
    -16.50
     Nar
    -16.13
     cigar
    -16.00
    搪
    -15.13
     SAS
    -15.00
    笮
    -15.00
    POSITIVE LOGITS
    黄
    54.00
    黃
    52.25
     yellow
    45.25
     �
    43.50
    Yellow
    43.50
    黄色
    43.50
     Yellow
    43.00
     YELLOW
    39.25
    -yellow
    38.00
    yellow
    36.25
    Activations Density 0.132%

    No Known Activations