© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15459
    Prev
    Next
    INDEX
    Explanations

    say "al"

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

    No Comments

    Negative Logits
    濡
    -23.38
    润滑
    -21.00
    润滑油
    -20.88
    触
    -19.13
    Touches
    -19.00
    黏
    -18.88
    橡胶
    -18.63
    rub
    -18.50
    atten
    -18.38
    粘
    -18.25
    POSITIVE LOGITS
     Al
    20.00
    -al
    20.00
    藻
    19.88
    alie
    19.38
     alarm
    19.38
    erek
    19.13
    ALLOC
    19.13
     allocator
    19.13
    alk
    19.00
    allo
    18.75
    Activations Density 5.135%

    No Known Activations