© 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. 15247
    Prev
    Next
    INDEX
    Explanations

    [E] => [E]

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

    No Comments

    Negative Logits
    �
    -21.00
    膠
    -19.50
    舞蹈
    -19.13
    сти
    -18.75
    胶
    -18.63
    大理
    -18.38
     Domino
    -17.75
     Tort
    -17.75
    科比
    -17.75
    TEX
    -17.63
    POSITIVE LOGITS
    ahn
    14.94
    flamm
    14.75
    anh
    14.31
    eah
    14.06
    .Foundation
    13.88
    .eu
    13.63
    OAuth
    13.63
    hydr
    13.56
     hydr
    13.44
    ivr
    13.31
    Activations Density 0.020%

    No Known Activations