© 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. 2910
    Prev
    Next
    INDEX
    Explanations

    say "降"

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

    No Comments

    Negative Logits
     Pet
    -24.63
    pet
    -22.25
    Pet
    -22.13
    .pet
    -22.00
     pet
    -21.50
     pets
    -21.00
    _pet
    -19.50
     emulation
    -18.75
     Str
    -18.38
     Fil
    -17.88
    POSITIVE LOGITS
    (desc
    24.25
    	desc
    21.75
     desc
    21.25
    desc
    21.25
     Des
    21.00
     des
    20.50
    Desc
    20.50
    Des
    20.13
     reg
    19.75
     eq
    19.63
    Activations Density 0.073%

    No Known Activations