© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 114068
    Prev
    Next
    INDEX
    Explanations

    expressions of pleasure or greeting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unre
    -0.14
    -ret
    -0.13
    oins
    -0.12
     wag
    -0.12
     rejo
    -0.12
    ilig
    -0.12
     econom
    -0.11
     clen
    -0.11
    )}}
    -0.11
     >>↵↵
    -0.11
    POSITIVE LOGITS
     greeting
    0.13
     welcoming
    0.11
     greetings
    0.10
     welcome
    0.10
     greet
    0.10
     friendly
    0.10
     welcomes
    0.10
     warmly
    0.09
     greeted
    0.09
     hello
    0.09
    Activations Density 0.013%

    No Known Activations