© 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. 92667
    Prev
    Next
    INDEX
    Explanations

    dialogue interjections, code structure

    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
     [...
    -0.12
    á»ı
    -0.12
    .Edit
    -0.11
     [...]↵↵
    -0.11
     countless
    -0.10
    /of
    -0.10
     Niet
    -0.10
     thumb
    -0.10
     teammate
    -0.10
    )this
    -0.10
    POSITIVE LOGITS
     OK
    0.13
     alright
    0.13
    Well
    0.13
     yeah
    0.13
     okay
    0.12
    ?”
    0.12
     Alright
    0.12
     sorry
    0.12
    OK
    0.12
     Well
    0.12
    Activations Density 0.002%

    No Known Activations