© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 32638
    Prev
    Next
    INDEX
    Explanations

    determine or understand

    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
     поба
    -0.09
    ä»ĭ
    -0.09
    icode
    -0.09
     недел
    -0.09
     feas
    -0.08
     doub
    -0.08
    gunakan
    -0.08
     Explanation
    -0.08
     Pierce
    -0.08
    =<?=
    -0.08
    POSITIVE LOGITS
     determination
    0.29
     determine
    0.26
    ç¡®å®ļ
    0.22
     determined
    0.21
     determines
    0.21
     Determin
    0.20
     Determine
    0.20
     zjist
    0.19
     determin
    0.19
     determining
    0.19
    Activations Density 0.227%

    No Known Activations