© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14179
    Prev
    Next
    INDEX
    Explanations

    say "space"

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

    No Comments

    Negative Logits
    饵
    -17.25
    砒
    -17.13
    /apple
    -16.13
     Deliver
    -15.44
    ovie
    -15.44
    螽
    -15.31
    团伙
    -14.81
    حمل
    -14.75
     addTarget
    -14.75
    镇政府
    -14.63
    POSITIVE LOGITS
    空间
    56.25
     space
    51.00
    的空间
    49.75
    空間
    47.50
    space
    46.50
     Space
    45.75
    Space
    45.50
     spaces
    45.00
    spaces
    43.50
    SPACE
    43.50
    Activations Density 0.644%

    No Known Activations