© 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. 493
    Prev
    Next
    INDEX
    Explanations

    say "mountain names"

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

    No Comments

    Negative Logits
     Croatian
    -21.50
    圩
    -19.50
     Telegram
    -19.13
     CC
    -18.88
     Kad
    -18.50
     KC
    -18.50
     Ukr
    -18.50
     Nigerian
    -18.13
    沭
    -18.00
     Africans
    -17.88
    POSITIVE LOGITS
    岳
    35.00
    泰山
    30.75
    岱
    24.25
    衡阳
    23.38
    南山
    23.00
    泰安
    22.38
     Mount
    21.88
    嵩
    21.88
    海淀
    21.50
    山
    21.38
    Activations Density 0.048%

    No Known Activations