© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1695
    Prev
    Next
    INDEX
    Explanations

    say construction

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

    No Comments

    Negative Logits
    atha
    -20.13
    auth
    -19.63
     auth
    -19.38
    	auth
    -18.50
     Auth
    -18.25
    .auth
    -18.25
    .Auth
    -17.88
    -auth
    -17.88
    _auth
    -17.50
     Authenticate
    -17.50
    POSITIVE LOGITS
    构造
    20.63
     construction
    18.50
     pixel
    18.38
    施工
    18.25
     pain
    18.13
    html
    18.13
     Construct
    18.13
    Instrument
    18.13
    MSN
    18.00
    乐器
    17.88
    Activations Density 0.281%

    No Known Activations