© 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. 14557
    Prev
    Next
    INDEX
    Explanations

    identifiers

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

    No Comments

    Negative Logits
    RAP
    -16.75
     Roberts
    -16.50
    уй
    -15.38
     shack
    -14.81
    checker
    -14.69
     viện
    -14.69
    VIC
    -14.56
     onBindViewHolder
    -14.44
    罗
    -14.25
    白银
    -14.25
    POSITIVE LOGITS
    maal
    17.25
    dbc
    16.75
    E
    16.75
    am
    16.50
    aley
    16.00
    �
    16.00
    EObject
    16.00
    不怕
    15.75
    hma
    15.69
    amus
    15.69
    Activations Density 0.483%

    No Known Activations