© 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. 14592
    Prev
    Next
    INDEX
    Explanations

    restaurant descriptions

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

    No Comments

    Negative Logits
    !’
    -17.13
    theless
    -17.00
     %=
    -16.88
     />'
    -16.63
    ",-
    -16.50
    …↵↵↵
    -16.13
     :↵↵↵↵
    -16.13
    尔斯
    -16.00
    snow
    -15.88
    ’↵↵
    -15.75
    POSITIVE LOGITS
     Hodg
    18.00
     Mand
    16.75
     Kend
    16.25
    cob
    16.25
    ager
    15.06
     sag
    15.00
     mort
    14.88
    circ
    14.63
    VR
    14.56
     CPR
    14.06
    Activations Density 0.231%

    No Known Activations