© 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. 14006
    Prev
    Next
    INDEX
    Explanations

    interview with

    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
     objection
    -0.10
     reminder
    -0.10
     Alert
    -0.10
     urgently
    -0.09
     reminding
    -0.09
     alerted
    -0.09
     presentations
    -0.09
    Proposal
    -0.09
     Proposal
    -0.09
    /cart
    -0.09
    POSITIVE LOGITS
     interview
    0.70
     Interview
    0.64
     interviewed
    0.62
     interviews
    0.61
    Interview
    0.60
     interviewer
    0.55
     Interviews
    0.54
     interviewing
    0.48
     entrev
    0.41
    erview
    0.29
    Activations Density 0.429%

    No Known Activations