© 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. 1968
    Prev
    Next
    INDEX
    Explanations

    media topics

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

    No Comments

    Negative Logits
    媒体
    -57.25
     media
    -55.00
    media
    -51.25
     Media
    -49.25
    Media
    -48.50
    媒體
    -47.00
    -media
    -46.00
    MEDIA
    -45.75
     MEDIA
    -45.25
    _media
    -45.00
    POSITIVE LOGITS
    盐
    18.75
    sal
    15.69
    �
    15.44
     Unix
    14.94
    igit
    14.69
    鹽
    14.63
     salt
    14.50
    ocs
    14.38
     sal
    14.13
    .datasets
    13.88
    Activations Density 0.113%

    No Known Activations