© 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. 19609
    Prev
    Next
    INDEX
    Explanations

    German passive constructions

    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
     concess
    -0.10
     Mitar
    -0.10
    ught
    -0.10
    лÑıли
    -0.10
     Beast
    -0.09
    582
    -0.09
    öyle
    -0.09
     ãĢī
    -0.09
    erc
    -0.09
    غÙĨ
    -0.09
    POSITIVE LOGITS
     worden
    0.19
     werden
    0.16
     become
    0.15
     zost
    0.14
     wird
    0.13
     wordt
    0.13
     becomes
    0.12
     被
    0.12
     Become
    0.12
     wurde
    0.12
    Activations Density 0.024%

    No Known Activations