© 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. 115202
    Prev
    Next
    INDEX
    Explanations

    mail or email related terms

    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
     specificity
    -0.09
    FACT
    -0.09
     cured
    -0.09
    edio
    -0.09
    à¹Īา
    -0.08
     dereg
    -0.08
     shortest
    -0.08
    ensi
    -0.08
    eon
    -0.08
    éĩı
    -0.08
    POSITIVE LOGITS
     me
    0.14
     us
    0.14
     mail
    0.11
     alerts
    0.11
    inator
    0.11
    -mail
    0.10
     mailing
    0.10
     inbox
    0.10
     Email
    0.10
    Email
    0.10
    Activations Density 0.014%

    No Known Activations