© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 13898
    Prev
    Next
    INDEX
    Explanations

    say compounds

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

    No Comments

    Negative Logits
    Insert
    -19.25
     INSERT
    -19.25
    _insert
    -18.25
    (space
    -18.00
    _INSERT
    -18.00
    	insert
    -17.88
    Inserted
    -17.88
    插入
    -17.88
     insert
    -17.75
     Insert
    -17.75
    POSITIVE LOGITS
    成分
    19.50
     compounds
    19.38
    提取
    18.50
    酚
    18.50
     component
    18.13
     compound
    18.00
    成份
    18.00
     extracts
    17.88
    �
    17.50
     extraction
    17.50
    Activations Density 0.302%

    No Known Activations