© 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
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 15555
    Prev
    Next
    INDEX
    Explanations

    fraction numerator

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

    No Comments

    Negative Logits
    罅
    -17.25
    试探
    -17.00
    probe
    -16.88
    sandbox
    -16.50
     DNC
    -16.38
    eração
    -16.13
    getSession
    -15.81
     Mara
    -15.81
    uç
    -15.75
    (tc
    -15.56
    POSITIVE LOGITS
    \
    19.25
     \
    15.31
    \_
    14.06
     blinded
    13.88
    \application
    13.75
    _WINDOW
    13.63
    \modules
    13.50
    .cli
    13.06
    ��
    13.00
    Wi
    13.00
    Activations Density 0.011%

    No Known Activations