© 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. 14435
    Prev
    Next
    INDEX
    Explanations

    [9] => [9]

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

    No Comments

    Negative Logits
    天花板
    -19.13
     xuân
    -19.13
    小伙子
    -19.00
     setAddress
    -18.88
    ocity
    -18.50
     thunk
    -18.50
    Thunk
    -18.38
     Quincy
    -18.13
    ộc
    -18.13
    (gc
    -18.00
    POSITIVE LOGITS
    Br
    17.38
     pat
    16.75
    Bl
    15.38
    br
    15.31
     St
    15.25
     Bray
    14.81
    Em
    14.75
    bn
    14.19
     Br
    14.19
    raph
    14.19
    Activations Density 0.127%

    No Known Activations