© 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. 15226
    Prev
    Next
    INDEX
    Explanations

    zero

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

    No Comments

    Negative Logits
     Shake
    -21.38
    (le
    -20.38
    zk
    -19.13
     lept
    -19.13
    angler
    -18.88
     zk
    -18.50
    akte
    -18.38
    лом
    -18.25
    _LE
    -18.00
    boom
    -18.00
    POSITIVE LOGITS
    0
    19.50
    エン
    13.56
     equity
    13.44
    メッ
    13.38
    ecal
    13.38
     Cheer
    13.25
    .machine
    13.19
     cluster
    13.06
    盾
    12.25
     fare
    12.19
    Activations Density 0.019%

    No Known Activations