© 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. 2364
    Prev
    Next
    INDEX
    Explanations

    say net

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

    No Comments

    Negative Logits
     network
    -31.00
    (network
    -30.38
    -network
    -30.00
    network
    -29.50
     Network
    -28.63
    网络
    -28.13
     NETWORK
    -28.13
    在网络
    -27.63
     networks
    -27.50
    (Network
    -27.13
    POSITIVE LOGITS
     net
    16.13
    Relation
    15.81
    壶
    15.44
     Relations
    15.31
     relation
    15.25
    韶
    15.25
    Relations
    15.19
     relations
    15.06
     Relation
    14.63
    relation
    14.31
    Activations Density 0.030%

    No Known Activations