© 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. 2815
    Prev
    Next
    INDEX
    Explanations

    say "专"

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

    No Comments

    Negative Logits
    [idx
    -18.75
    idx
    -18.50
    arr
    -17.50
    (idx
    -17.38
     idx
    -17.38
    (metric
    -17.00
    _idxs
    -16.88
    ény
    -16.88
     arr
    -16.75
     erase
    -16.75
    POSITIVE LOGITS
    专
    39.50
     spec
    36.75
     Spec
    32.50
    	spec
    32.25
    spec
    31.00
    (spec
    29.75
    Spec
    28.38
    .spec
    27.63
    _spec
    25.75
    特
    25.38
    Activations Density 0.045%

    No Known Activations