© 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. 15405
    Prev
    Next
    INDEX
    Explanations

    say banana

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

    No Comments

    Negative Logits
     Falk
    -22.63
     Elli
    -21.63
    Knight
    -21.50
    bnb
    -21.13
    �
    -21.00
    Wolf
    -20.88
    ockets
    -20.75
    орт
    -20.75
     Montgomery
    -20.38
     Wolf
    -20.25
    POSITIVE LOGITS
     Willow
    24.25
     Mojo
    22.63
     mojo
    22.00
    蕉
    21.63
     banana
    20.50
     Brady
    20.50
    香蕉
    20.25
    芗
    20.00
    ilar
    20.00
     Mush
    19.25
    Activations Density 5.000%

    No Known Activations