© 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. 2822
    Prev
    Next
    INDEX
    Explanations

    potatoes

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

    No Comments

    Negative Logits
     Gen
    -19.50
     gen
    -18.00
     Legend
    -17.75
    Gen
    -17.75
     Leg
    -17.25
    visit
    -17.25
    (gen
    -17.13
    .cur
    -16.75
    Visitor
    -16.75
     Vis
    -16.75
    POSITIVE LOGITS
     Pete
    34.50
     Peters
    29.00
     Peterson
    27.13
     Pert
    26.75
     Perez
    26.63
     PET
    26.13
     Pot
    25.75
    Pet
    25.50
     pert
    25.50
    彼得
    25.38
    Activations Density 0.057%

    No Known Activations