© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14568
    Prev
    Next
    INDEX
    Explanations

    say 9

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

    No Comments

    Negative Logits
     Wizards
    -23.13
    ewire
    -18.88
     Jeremiah
    -17.50
     Kang
    -17.50
    燃气
    -17.38
    杰
    -16.75
    berger
    -16.50
    inging
    -16.13
    Jer
    -16.00
     Jerome
    -15.88
    POSITIVE LOGITS
    -d
    20.38
     Sha
    18.75
    Sha
    17.88
     seventh
    17.63
    tica
    17.13
     Seventh
    16.88
    _sh
    16.50
     �
    16.38
    asha
    16.25
    seven
    16.25
    Activations Density 0.101%

    No Known Activations