© 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. 15898
    Prev
    Next
    INDEX
    Explanations

    say anatomical movements

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

    No Comments

    Negative Logits
    山区
    -19.00
    赛区
    -18.25
    атур
    -18.00
    运河
    -17.88
    温泉
    -17.50
    -company
    -17.25
    化工
    -16.88
    森林公园
    -16.75
    中关村
    -16.75
    清洗
    -16.25
    POSITIVE LOGITS
     extension
    17.88
     Fowler
    16.00
    lord
    15.63
     abducted
    15.50
    弯曲
    15.44
    伸
    15.31
     ext
    15.13
     Extension
    15.06
    	Ext
    14.81
     bends
    14.75
    Activations Density 0.105%

    No Known Activations