© 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. 25225
    Prev
    Next
    INDEX
    Explanations

    meeting or contacting people

    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
    Negative Logits
     wield
    -0.09
     wielding
    -0.08
    av
    -0.08
    avra
    -0.08
     fla
    -0.08
    avit
    -0.08
    arf
    -0.08
    erb
    -0.08
    ellt
    -0.08
     enforcing
    -0.08
    POSITIVE LOGITS
     interviewing
    0.16
     interviewed
    0.15
     contact
    0.15
     contacting
    0.14
     kontakt
    0.14
     appe
    0.14
     contacted
    0.14
    ê²Į
    0.13
     impress
    0.13
     Encounter
    0.13
    Activations Density 0.265%

    No Known Activations