© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1114
    Prev
    Next
    INDEX
    Explanations

    acid => rain

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

    No Comments

    Negative Logits
    酸
    -57.25
     acid
    -54.00
    acid
    -52.50
     Acid
    -51.75
     acids
    -50.50
     acidic
    -43.25
     acidity
    -41.75
    Ac
    -41.75
    _ac
    -40.50
    -ac
    -38.50
    POSITIVE LOGITS
    羽
    14.94
    lambda
    14.00
    amente
    13.31
    umo
    13.25
    安全
    13.19
    彩
    12.88
     Barn
    12.81
     film
    12.69
     WP
    12.56
    film
    12.50
    Activations Density 0.102%

    No Known Activations