© 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. 55707
    Prev
    Next
    INDEX
    Explanations

    Turkish word beginnings

    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
     ulaÅŁ
    -0.13
     KiÅŁ
    -0.12
     Åŀehir
    -0.11
     AraÅŁtır
    -0.11
     ÃĸÄŁren
    -0.11
     DeÄŁer
    -0.11
     Ä°nsan
    -0.11
     MÃ¼ÅŁ
    -0.11
     obr
    -0.11
     Ä°li
    -0.11
    POSITIVE LOGITS
     ve
    0.16
    asyon
    0.11
    ipl
    0.11
     Bir
    0.11
    iy
    0.11
    vey
    0.10
    roller
    0.10
    rey
    0.10
    iye
    0.10
    ̧
    0.10
    Activations Density 0.093%

    No Known Activations