© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15841
    Prev
    Next
    INDEX
    Explanations

    say touch

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

    No Comments

    Negative Logits
    藻
    -20.50
     alarm
    -19.50
    erek
    -19.25
    alie
    -19.13
    ALLOC
    -19.13
    rek
    -19.13
    -al
    -19.00
    alk
    -18.75
    Alarm
    -18.75
     allocator
    -18.63
    POSITIVE LOGITS
    濡
    22.75
    触
    19.50
    润滑油
    19.38
    润滑
    19.25
    Touches
    18.75
    柔
    18.50
    柔软
    18.38
    touch
    18.00
    atten
    18.00
    ATT
    17.88
    Activations Density 4.743%

    No Known Activations