© 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. 25648
    Prev
    Next
    INDEX
    Explanations

    Email related phrases

    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
    lero
    -0.10
     Gal
    -0.10
    line
    -0.10
     Welch
    -0.10
    lay
    -0.09
     rave
    -0.09
    innie
    -0.09
     hin
    -0.09
     typ
    -0.08
    link
    -0.08
    POSITIVE LOGITS
    /chat
    0.12
    .mime
    0.12
    /text
    0.11
     newsletters
    0.11
     blast
    0.10
     alerts
    0.10
     alert
    0.10
     marketing
    0.10
    /facebook
    0.10
     address
    0.10
    Activations Density 0.027%

    No Known Activations