© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15531
    Prev
    Next
    INDEX
    Explanations

    say aquarium

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

    No Comments

    Negative Logits
    院士
    -17.00
    酮
    -16.88
    仗
    -16.75
    struk
    -16.50
    /address
    -16.38
     Jad
    -16.25
     adr
    -16.13
    埽
    -15.69
    抹
    -15.69
    (ad
    -15.31
    POSITIVE LOGITS
     aquarium
    28.50
     Aquarium
    25.63
     aquatic
    22.50
    aqu
    18.63
     tank
    18.50
     aqu
    18.13
    Spawn
    17.75
    养护
    17.38
    Aqu
    17.25
    Tank
    17.13
    Activations Density 0.187%

    No Known Activations