© 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. 16099
    Prev
    Next
    INDEX
    Explanations

    reference counting

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

    No Comments

    Negative Logits
    ↙
    -20.25
    老爸
    -18.13
    两天
    -17.88
     thử
    -17.00
     Seven
    -17.00
     Profession
    -16.63
    getParam
    -16.50
    _days
    -16.25
     getParent
    -16.25
     Pentagon
    -16.13
    POSITIVE LOGITS
    Opaque
    16.00
     {@
    15.63
    (bundle
    15.50
     slime
    14.75
    {@
    14.31
    氘
    13.94
    琨
    13.38
     Hose
    13.25
     avalanche
    13.00
    obo
    12.88
    Activations Density 0.337%

    No Known Activations