© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2548
    Prev
    Next
    INDEX
    Explanations

    say "hyp" words

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

    No Comments

    Negative Logits
     emitted
    -19.13
     Emit
    -18.63
     emit
    -18.50
    emit
    -18.38
     emission
    -18.13
     emits
    -17.88
    发
    -17.25
    呜
    -17.25
    咕
    -17.25
     emissions
    -16.50
    POSITIVE LOGITS
     hyp
    96.00
    hyp
    89.50
     Hyp
    84.00
     hypo
    54.00
     hyper
    52.75
    hyper
    52.50
     hypothesis
    52.25
    Hyper
    51.25
     Hyper
    51.00
     hypers
    50.50
    Activations Density 0.139%

    No Known Activations