© 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. 40126
    Prev
    Next
    INDEX
    Explanations

    words starting with tw

    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
     âĹĦ
    -0.11
    oles
    -0.10
    ISE
    -0.09
     Lonely
    -0.09
    è¡
    -0.09
    ead
    -0.09
    wart
    -0.09
    isser
    -0.09
    ewed
    -0.09
    oothing
    -0.08
    POSITIVE LOGITS
     tw
    0.23
     Tw
    0.19
    Tw
    0.14
    tw
    0.14
    -tw
    0.13
    ilio
    0.12
     TW
    0.12
    addle
    0.12
    isted
    0.12
    .tw
    0.11
    Activations Density 0.037%

    No Known Activations