© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 3277
    Prev
    Next
    INDEX
    Explanations

    say "end"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     Number
    -16.13
     Figure
    -15.50
     Heading
    -14.94
    aben
    -14.81
     Question
    -14.56
    ild
    -14.38
    ünd
    -14.31
     Bermuda
    -14.25
    setType
    -14.25
     Country
    -14.06
    POSITIVE LOGITS
     endpoints
    20.13
    (endpoint
    19.50
     endpoint
    18.00
    album
    17.88
    _album
    17.75
    端
    17.25
    报社
    17.13
    报业
    17.13
    end
    17.00
    effect
    17.00
    Activations Density 0.055%

    No Known Activations