© 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. 34221
    Prev
    Next
    INDEX
    Explanations

    salutations and names in communication

    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
     swe
    -0.08
     Boyd
    -0.08
     perm
    -0.08
     Reserve
    -0.08
    081
    -0.08
    osen
    -0.08
     our
    -0.08
     tran
    -0.07
    eter
    -0.07
     sculpt
    -0.07
    POSITIVE LOGITS
     powerless
    0.11
    -placeholder
    0.11
    "),"
    0.11
     investigators
    0.10
    antha
    0.10
     mutil
    0.10
     programmes
    0.09
     Tee
    0.09
     anonymous
    0.09
     _:
    0.09
    Activations Density 0.009%

    No Known Activations