© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14947
    Prev
    Next
    INDEX
    Explanations

    say 9

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

    No Comments

    Negative Logits
    樽
    -20.50
     stun
    -19.63
     Jord
    -19.38
    .substr
    -18.63
     St
    -18.50
     Stan
    -18.38
    St
    -18.25
     Stuart
    -17.88
    STRUCTOR
    -17.88
    Jordan
    -17.38
    POSITIVE LOGITS
     cape
    17.50
    plx
    17.13
    erm
    16.50
     cooling
    15.63
    loom
    15.31
    邈
    15.13
    华侨
    15.00
    ец
    14.69
    .Automation
    14.63
    lications
    14.56
    Activations Density 0.081%

    No Known Activations