© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15030
    Prev
    Next
    INDEX
    Explanations

    9

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

    No Comments

    Negative Logits
    ije
    -17.88
     Locke
    -15.06
    jal
    -14.75
     bada
    -14.75
    텔
    -13.88
     eid
    -13.81
     azimuth
    -13.75
    iou
    -13.69
    zie
    -13.56
    ’
    -13.19
    POSITIVE LOGITS
     màn
    16.63
    农
    16.38
    竹
    16.00
    ariat
    15.56
    banks
    15.25
     示
    14.75
    rics
    14.56
    黎
    14.50
    泥
    14.44
    llib
    14.38
    Activations Density 0.022%

    No Known Activations