© 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. 2209
    Prev
    Next
    INDEX
    Explanations

    say per

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

    No Comments

    Negative Logits
    资
    -18.13
    LIB
    -17.75
    TER
    -17.38
    termination
    -16.88
    .registration
    -16.75
    秭
    -16.63
     lib
    -16.38
     terminals
    -16.13
    條
    -16.13
    bins
    -15.94
    POSITIVE LOGITS
     Per
    43.25
    (per
    42.75
    Per
    41.25
    -per
    40.75
     perm
    38.00
     perfection
    36.25
    _per
    36.25
     per
    36.00
    /per
    36.00
    .per
    34.75
    Activations Density 0.078%

    No Known Activations