© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2120
    Prev
    Next
    INDEX
    Explanations

    say elect

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

    No Comments

    Negative Logits
    套
    -28.25
    甲
    -21.50
     Ver
    -20.50
    .ser
    -20.13
    .ver
    -20.13
    -ver
    -20.00
    偏差
    -19.88
     dim
    -19.63
     ver
    -19.50
    Ver
    -19.50
    POSITIVE LOGITS
     elect
    57.25
     Elect
    54.75
    elect
    38.50
    Elect
    37.75
     electrom
    32.50
     élect
    30.63
    -elect
    29.25
     ELECT
    28.50
     элект
    27.50
     electr
    26.63
    Activations Density 0.060%

    No Known Activations