© 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. 16366
    Prev
    Next
    INDEX
    Explanations

    say weight

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

    No Comments

    Negative Logits
     racer
    -16.38
    谍
    -16.25
    宣言
    -16.25
     CreateMap
    -16.13
     Intelli
    -16.13
     createAction
    -16.13
    暾
    -16.00
     фин
    -15.88
    _race
    -15.75
    客栈
    -15.69
    POSITIVE LOGITS
     weight
    63.75
    weight
    59.75
     weights
    59.25
     Weight
    57.50
    Weight
    56.75
     weigh
    54.50
    重量
    54.00
     WEIGHT
    53.00
    weights
    52.25
    (weight
    52.25
    Activations Density 0.337%

    No Known Activations