© 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. 1076
    Prev
    Next
    INDEX
    Explanations

    do not say English

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

    No Comments

    Negative Logits
     English
    -57.25
    英语
    -54.75
     english
    -53.25
    English
    -52.75
    英
    -48.25
     England
    -44.75
    english
    -44.25
    英文
    -44.00
     англий
    -43.50
    England
    -41.75
    POSITIVE LOGITS
    原子
    17.38
    树
    15.50
    氢
    15.13
     trees
    14.88
    atoms
    14.69
    -tree
    14.44
     FirebaseFirestore
    14.44
    tree
    14.31
    cs
    14.31
    tokenId
    14.19
    Activations Density 0.184%

    No Known Activations