© 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. 51006
    Prev
    Next
    INDEX
    Explanations

    professions and practices

    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
     unexpected
    -0.13
     hopefully
    -0.12
     unexpectedly
    -0.11
     tremend
    -0.11
     Moments
    -0.10
     intuit
    -0.10
     newfound
    -0.10
     moments
    -0.10
     unforgettable
    -0.10
    anine
    -0.10
    POSITIVE LOGITS
     hired
    0.23
     specialize
    0.20
     specializing
    0.19
     usually
    0.19
     freelance
    0.18
     typically
    0.17
     specializes
    0.17
     hire
    0.17
     employed
    0.17
     specialization
    0.16
    Activations Density 0.096%

    No Known Activations