© 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. 15339
    Prev
    Next
    INDEX
    Explanations

    citation details

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

    No Comments

    Negative Logits
    ping
    -16.63
    oleans
    -14.06
    .ordinal
    -13.94
    Chelsea
    -13.81
    ordinate
    -13.81
    heet
    -13.81
    rica
    -13.63
    输出
    -13.63
    heets
    -13.56
    虹桥
    -13.56
    POSITIVE LOGITS
    fé
    16.25
    至於
    15.63
     travellers
    15.63
    ikip
    15.50
     Duffy
    15.50
    gue
    15.44
    Gil
    15.31
     zam
    15.25
    scar
    15.19
    Dar
    15.00
    Activations Density 0.064%

    No Known Activations