© 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. 14011
    Prev
    Next
    INDEX
    Explanations

    names like Andrew or Andy

    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
    urst
    -0.08
    Camb
    -0.08
    stras
    -0.08
    igm
    -0.08
     lul
    -0.08
    enso
    -0.08
     dem
    -0.08
     typ
    -0.07
     Camb
    -0.07
     promot
    -0.07
    POSITIVE LOGITS
     Rooney
    0.12
    اء
    0.11
     warp
    0.11
     era
    0.10
    WAR
    0.10
     enc
    0.10
    _ajax
    0.10
    -ne
    0.10
    ots
    0.10
     alphabet
    0.10
    Activations Density 0.004%

    No Known Activations