© 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. 14940
    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
    plit
    -17.50
     Hop
    -17.38
    VP
    -17.25
    _vp
    -16.88
     vp
    -16.75
    velt
    -16.63
     Bret
    -16.63
    stp
    -16.50
    VT
    -16.38
    vit
    -16.25
    POSITIVE LOGITS
    Rio
    19.00
    abbo
    18.25
     rac
    17.75
     radiation
    17.75
    rice
    17.63
     resc
    17.13
     Bacon
    17.13
     reck
    17.00
    inson
    17.00
     RECE
    16.88
    Activations Density 0.690%

    No Known Activations