© 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. 15482
    Prev
    Next
    INDEX
    Explanations

    say speculation

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

    No Comments

    Negative Logits
    rock
    -18.38
    locked
    -18.13
    石家
    -17.63
    嘴巴
    -17.50
    bash
    -16.88
    逵
    -16.88
    樘
    -16.50
    productId
    -16.38
    /bootstrap
    -16.25
     approvals
    -16.13
    POSITIVE LOGITS
     conject
    27.25
    猜想
    24.38
     suspects
    23.50
     hypo
    23.38
     speculation
    23.00
    猜测
    23.00
     guess
    22.13
     suspicion
    21.38
     suspect
    21.25
     speculate
    21.13
    Activations Density 0.210%

    No Known Activations