© 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. 2287
    Prev
    Next
    INDEX
    Explanations

    say "hyper"

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

    No Comments

    Negative Logits
    Mor
    -17.13
    精
    -16.25
     resolutions
    -15.63
    _pen
    -15.50
     Sem
    -15.25
     poil
    -14.50
    道德
    -14.31
    造纸
    -14.25
     moral
    -13.69
    creen
    -13.63
    POSITIVE LOGITS
     hyper
    77.00
    Hyper
    75.50
    hyper
    75.00
     Hyper
    74.00
     hyp
    65.50
    _hyper
    64.50
    hyp
    64.50
     Hyp
    61.25
     hypers
    47.25
     hypo
    46.00
    Activations Density 0.092%

    No Known Activations