© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 28418
    Prev
    Next
    INDEX
    Explanations

    Rodgers salary advertisement

    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
    apos
    -0.10
     "..
    -0.09
     "...
    -0.09
    dcc
    -0.09
    Alright
    -0.09
     Nem
    -0.09
    Diese
    -0.09
    enis
    -0.09
    ecom
    -0.09
     sill
    -0.09
    POSITIVE LOGITS
    âĸł
    0.13
     columns
    0.12
     column
    0.11
     anon
    0.11
    advertisement
    0.11
     Readers
    0.10
    Advertisement
    0.10
    .—
    0.10
     âĸł
    0.10
     rude
    0.09
    Activations Density 0.443%

    No Known Activations