© 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. 14829
    Prev
    Next
    INDEX
    Explanations

    say Black

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

    No Comments

    Negative Logits
    /env
    -17.50
    牝
    -17.13
     deutsch
    -16.88
    保护
    -16.88
    退市
    -16.75
    legt
    -16.13
    ateur
    -16.00
    烝
    -16.00
     getInt
    -15.94
     Toshiba
    -15.81
    POSITIVE LOGITS
    驴
    14.00
     Afro
    13.94
    Unity
    13.94
    Atlanta
    13.81
    mesh
    13.81
    美
    13.75
    芝麻
    13.75
     Harlem
    13.75
    Beauty
    13.75
    Black
    13.63
    Activations Density 0.138%

    No Known Activations