© 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. 999
    Prev
    Next
    INDEX
    Explanations

    carbon capture

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

    No Comments

    Negative Logits
    桴
    -19.13
    棺
    -19.13
    感冒
    -18.75
    髋
    -18.50
    鬓
    -17.50
    感染者
    -17.38
    礼物
    -17.00
    患儿
    -17.00
     haircut
    -17.00
     radios
    -17.00
    POSITIVE LOGITS
    化工
    18.25
     Steam
    17.63
    废水
    17.13
     recycle
    16.63
    宁夏
    16.50
    厂区
    16.25
    urd
    16.13
    煤气
    16.13
    钠
    16.13
    油气
    15.81
    Activations Density 0.101%

    No Known Activations