© 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. 14541
    Prev
    Next
    INDEX
    Explanations

    person names

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

    No Comments

    Negative Logits
    Atlas
    -21.63
     Atlas
    -19.50
     atlas
    -18.63
    绶
    -18.25
    존
    -17.88
    aidu
    -16.75
    海岛
    -16.63
     Blueprint
    -16.63
    ousse
    -16.25
    .columnHeader
    -16.13
    POSITIVE LOGITS
    KEN
    18.25
    Ｋ
    17.25
    ken
    16.00
    ook
    15.44
    ooks
    15.13
     kl
    14.94
    KER
    14.81
     Quar
    14.75
    韓
    14.56
     mop
    14.25
    Activations Density 0.973%

    No Known Activations