© 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. 2543
    Prev
    Next
    INDEX
    Explanations

    say "hyp"

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

    No Comments

    Negative Logits
    Den
    -20.25
     ret
    -17.50
    ret
    -17.13
     Ret
    -17.00
     Den
    -17.00
     Config
    -17.00
    发
    -16.63
     Pres
    -16.50
    den
    -16.38
     Perc
    -16.38
    POSITIVE LOGITS
     hyp
    30.25
     Hyp
    28.63
     hypothesis
    27.38
     Hyper
    26.88
    hyper
    26.75
    Hyper
    26.63
    char
    26.25
     hypotheses
    26.13
     char
    26.00
     hyper
    26.00
    Activations Density 0.058%

    No Known Activations