© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1430
    Prev
    Next
    INDEX
    Explanations

    [fruit] => [fruit]

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

    No Comments

    Negative Logits
    水果
    -45.25
     fruit
    -44.00
     fruits
    -40.50
     Fruit
    -39.75
    fruit
    -37.50
     fruity
    -35.50
    果
    -34.25
    果树
    -33.25
    苹果
    -31.38
    果实
    -30.00
    POSITIVE LOGITS
     Chemistry
    18.38
    Chem
    17.88
     chemistry
    16.13
    Engineering
    16.13
    化学
    15.94
     Chem
    15.63
     Engineers
    15.56
     nitrogen
    15.25
     Engineering
    14.94
     engineer
    14.88
    Activations Density 0.102%

    No Known Activations