© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 420
    Prev
    Next
    INDEX
    Explanations

    say "car brands"

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

    No Comments

    Negative Logits
     Crypt
    -20.13
    Wallet
    -20.00
    _wallet
    -19.00
     crypto
    -19.00
     publicKey
    -18.88
    Crypto
    -18.63
     pubkey
    -18.63
    wallet
    -18.63
     cryptography
    -18.63
     encryption
    -18.38
    POSITIVE LOGITS
    丰田
    31.88
     Toyota
    25.75
    工序
    23.63
    精益
    22.13
    Toyota
    21.75
    生产线
    21.13
     Suzuki
    20.88
    停产
    20.25
    本田
    20.13
    日产
    19.63
    Activations Density 0.100%

    No Known Activations