© 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. 1285
    Prev
    Next
    INDEX
    Explanations

    seed

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

    No Comments

    Negative Logits
     Seed
    -37.75
     seed
    -37.50
     seeds
    -36.50
    种子
    -35.00
     Seeds
    -34.75
    Seed
    -34.25
    seed
    -34.00
     Security
    -30.50
    _seed
    -30.25
     security
    -28.88
    POSITIVE LOGITS
    的语言
    18.38
    _cart
    18.25
    物理学
    18.13
     Cart
    18.00
    Cart
    17.00
    语言
    16.38
    _languages
    15.81
    _lang
    15.81
     language
    15.69
     Physics
    15.63
    Activations Density 0.080%

    No Known Activations