© 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. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 117287
    Prev
    Next
    INDEX
    Explanations

    times of day and email

    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
    ument
    -0.12
    los
    -0.12
    :host
    -0.11
    LOSS
    -0.11
     Centro
    -0.11
    eyer
    -0.11
    948
    -0.11
     Eduardo
    -0.11
     Deferred
    -0.11
    zel
    -0.11
    POSITIVE LOGITS
     emails
    0.10
     receive
    0.09
     email
    0.08
    lle
    0.07
     region
    0.07
     anew
    0.07
     receives
    0.07
     twice
    0.07
     vene
    0.07
     Email
    0.07
    Activations Density 0.002%

    No Known Activations