© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 745
    Prev
    Next
    INDEX
    Explanations

    commas

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

    No Comments

    Negative Logits
    TabIndex
    -19.38
    PCODE
    -17.00
    ajs
    -17.00
     SZ
    -16.75
     Grupo
    -16.75
    英镑
    -16.50
    walk
    -16.25
     perch
    -16.13
    ñ
    -16.00
    tribute
    -15.88
    POSITIVE LOGITS
     pros
    15.38
     flip
    14.44
     sour
    14.13
    soft
    13.38
    Bar
    13.31
    ob
    13.19
    ras
    13.19
     Bea
    12.88
    sol
    12.69
    Tip
    12.44
    Activations Density 1.529%

    No Known Activations