© 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. 14969
    Prev
    Next
    INDEX
    Explanations

    N/A

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

    No Comments

    Negative Logits
    aland
    -22.13
     sidewalk
    -19.63
    片区
    -19.38
     pedals
    -19.00
    ardi
    -19.00
     nid
    -19.00
    nid
    -18.38
     palate
    -18.25
    fds
    -18.00
    _PED
    -17.75
    POSITIVE LOGITS
     Kirby
    20.13
    jer
    19.88
    tam
    19.75
    cir
    19.25
    tower
    19.00
    ammer
    18.88
    泰州
    18.63
    阶梯
    18.50
    aggio
    18.38
    浩
    18.38
    Activations Density 0.886%

    No Known Activations