© 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. 2621
    Prev
    Next
    INDEX
    Explanations

    twist and touch

    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
    abo
    -0.10
    iren
    -0.09
     Grat
    -0.09
    766
    -0.09
     wed
    -0.09
    INCREMENT
    -0.09
    antic
    -0.09
    ç«
    -0.09
    .compose
    -0.08
    íĥĦ
    -0.08
    POSITIVE LOGITS
     twist
    0.78
     Twist
    0.62
     twists
    0.52
     touch
    0.48
     touches
    0.37
    touch
    0.35
     Touch
    0.35
    Touch
    0.33
    -tw
    0.30
    -touch
    0.30
    Activations Density 0.208%

    No Known Activations