© 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. 15081
    Prev
    Next
    INDEX
    Explanations

    parent‑child

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

    No Comments

    Negative Logits
    entar
    -17.38
    Ws
    -16.88
    essen
    -16.88
    CSR
    -16.50
    遥
    -16.38
    ess
    -16.00
    Rpc
    -15.88
    ônica
    -15.81
    aters
    -15.75
    ether
    -15.69
    POSITIVE LOGITS
     kale
    17.88
     kil
    17.50
    vig
    17.13
     k
    16.38
     Trout
    16.38
     brig
    16.25
     kd
    16.13
     Kend
    16.13
     plywood
    16.13
    quist
    15.94
    Activations Density 0.087%

    No Known Activations