© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15508
    Prev
    Next
    INDEX
    Explanations

    say "deserialize"

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

    No Comments

    Negative Logits
     arm
    -20.50
    arms
    -20.25
     Arm
    -20.00
     arms
    -19.13
    翅膀
    -18.88
    Arm
    -18.63
    reich
    -18.50
     Wings
    -18.50
     claw
    -18.38
     Arms
    -18.00
    POSITIVE LOGITS
    脱
    19.63
    deserialize
    18.50
    粜
    18.00
     deserialize
    17.13
    De
    17.00
     De
    16.50
    (de
    15.75
    沸腾
    15.69
    -des
    15.50
     Deserialize
    15.38
    Activations Density 1.237%

    No Known Activations