© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2276
    Prev
    Next
    INDEX
    Explanations

    metadata

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

    No Comments

    Negative Logits
     Rev
    -22.13
    rev
    -21.75
     rev
    -19.75
    Rev
    -17.88
     rel
    -16.50
     pos
    -16.13
     att
    -15.75
     Pos
    -15.63
    cheme
    -15.50
     cert
    -15.13
    POSITIVE LOGITS
     metadata
    69.50
     Metadata
    66.50
    metadata
    64.00
    (metadata
    64.00
    Metadata
    63.50
    _metadata
    59.00
    .metadata
    56.25
    _Metadata
    54.50
    _METADATA
    54.00
    -metadata
    51.75
    Activations Density 0.053%

    No Known Activations