© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 13934
    Prev
    Next
    INDEX
    Explanations

    say "capacity"

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

    No Comments

    Negative Logits
    帧
    -16.63
     �
    -15.56
    贱
    -15.25
    ichert
    -14.81
    运动
    -14.56
    .frame
    -14.44
    運動
    -14.44
    controllers
    -14.19
    gorithm
    -14.06
     saver
    -13.94
    POSITIVE LOGITS
     capacity
    67.50
     capacities
    62.75
     Capacity
    61.25
    capacity
    60.50
    Capacity
    59.50
    能力
    57.50
    _capacity
    56.25
     capability
    50.75
    能力和
    50.50
    .capacity
    50.00
    Activations Density 0.667%

    No Known Activations