© 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. 2940
    Prev
    Next
    INDEX
    Explanations

    say "dim"

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

    No Comments

    Negative Logits
    Leg
    -19.63
     leg
    -19.50
     SEG
    -18.88
     LEG
    -18.00
    LEG
    -18.00
    老人家
    -17.63
     Leg
    -17.63
     Legs
    -17.50
    segment
    -17.13
    leg
    -17.00
    POSITIVE LOGITS
    维
    49.75
     dim
    45.50
    (dim
    43.00
    Dim
    42.50
    dim
    41.75
     Dim
    40.75
    _dim
    39.75
     dimension
    39.50
     Dimension
    37.75
    .dim
    37.50
    Activations Density 0.055%

    No Known Activations