© 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. 15071
    Prev
    Next
    INDEX
    Explanations

    [2] => [0]

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

    No Comments

    Negative Logits
    nid
    -20.75
    ilik
    -19.50
    olon
    -19.25
     Blond
    -18.13
    olin
    -17.88
     condom
    -17.50
    oil
    -17.50
     Frid
    -17.38
    iline
    -17.25
    (cookie
    -17.25
    POSITIVE LOGITS
    auer
    15.88
     Rupert
    15.81
    DA
    15.63
    ainty
    14.81
     DG
    14.69
    agh
    14.56
    RS
    14.44
    dba
    14.31
    悬
    14.13
     Raptors
    13.88
    Activations Density 0.143%

    No Known Activations