© 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. 2953
    Prev
    Next
    INDEX
    Explanations

    say "residual"

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

    No Comments

    Negative Logits
    记
    -20.38
     recall
    -20.25
     remember
    -19.00
     recalls
    -18.75
    recall
    -18.63
    政
    -18.38
    記
    -18.13
     recalling
    -17.88
    remember
    -17.13
     recalled
    -17.00
    POSITIVE LOGITS
    示范
    20.13
    _residual
    18.00
     residual
    17.88
    残
    17.88
    乡村
    17.13
    植
    16.75
    (idx
    16.50
     pot
    16.25
    [idx
    16.13
    pot
    15.88
    Activations Density 0.153%

    No Known Activations