© 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. 15293
    Prev
    Next
    INDEX
    Explanations

    say 0

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

    No Comments

    Negative Logits
     Dodd
    -18.63
    mars
    -18.38
     zk
    -17.38
     Sark
    -17.25
     ect
    -16.63
    zik
    -16.63
     Kitty
    -16.50
    serter
    -16.25
    Vk
    -16.13
    渤
    -16.00
    POSITIVE LOGITS
    riangle
    18.63
    豌
    15.56
     triangle
    15.38
    ufe
    15.38
    ran
    14.94
    strained
    14.81
     IMDb
    14.75
    PACE
    14.75
    Triangle
    14.69
    ラン
    14.44
    Activations Density 0.008%

    No Known Activations