© 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. 2495
    Prev
    Next
    INDEX
    Explanations

    say meta

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

    No Comments

    Negative Logits
    mult
    -18.00
    ertext
    -16.38
    [opt
    -16.25
    .LA
    -16.25
    Mult
    -16.25
     Mult
    -16.00
    (fil
    -15.25
    睦
    -15.25
    BOSE
    -15.06
    	mock
    -15.00
    POSITIVE LOGITS
     meta
    50.75
    (meta
    48.00
    meta
    47.75
     Meta
    46.25
    Meta
    43.50
    .meta
    43.00
    	meta
    41.00
    _meta
    38.25
    -meta
    38.00
    /meta
    38.00
    Activations Density 0.245%

    No Known Activations