© 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. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 61908
    Prev
    Next
    INDEX
    Explanations

    kdesktop environment and qml

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     QSize
    -0.12
     QPoint
    -0.11
     lil
    -0.10
     QMap
    -0.09
     QTableWidgetItem
    -0.09
     dro
    -0.09
     QPointF
    -0.09
     quay
    -0.09
     QPixmap
    -0.09
     intimid
    -0.08
    POSITIVE LOGITS
     Q
    0.21
    .qml
    0.19
    Q
    0.16
    qml
    0.13
    .Q
    0.12
     q
    0.12
     moc
    0.12
    (Q
    0.11
     Harr
    0.11
    .q
    0.11
    Activations Density 0.014%

    No Known Activations