© 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. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 115703
    Prev
    Next
    INDEX
    Explanations

    welcomes and greetings

    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
    nos
    -0.13
    ubo
    -0.11
    usta
    -0.10
    ASF
    -0.10
    088
    -0.09
    eler
    -0.09
    ERY
    -0.09
    ws
    -0.09
     prem
    -0.09
    illac
    -0.09
    POSITIVE LOGITS
     spotted
    0.13
     recogn
    0.12
     welcome
    0.12
     welcomes
    0.11
     Hearing
    0.11
     spotting
    0.11
     welcomed
    0.11
     when
    0.11
     greeted
    0.11
     Welcome
    0.10
    Activations Density 0.045%

    No Known Activations