© 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. 14332
    Prev
    Next
    INDEX
    Explanations

    aircraft compartments

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

    No Comments

    Negative Logits
    ZE
    -17.38
    THREAD
    -16.63
     EVE
    -15.69
    厥
    -15.56
    Thread
    -15.56
    hör
    -15.06
    罗马
    -15.00
     createAction
    -14.81
    资源
    -14.56
    ène
    -14.50
    POSITIVE LOGITS
    forward
    18.25
    荚
    18.25
     compartments
    17.63
     Belly
    17.38
     fittings
    16.50
     compartment
    16.38
    壳
    16.25
    warts
    16.13
     mount
    16.13
     Fus
    16.00
    Activations Density 0.251%

    No Known Activations