© 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. 92367
    Prev
    Next
    INDEX
    Explanations

    east, west, southeast

    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
     Kath
    -0.10
    —from
    -0.10
     stu
    -0.09
    stra
    -0.09
    oha
    -0.09
     Mahar
    -0.09
     Suzuki
    -0.09
    leta
    -0.08
    uri
    -0.08
    nid
    -0.08
    POSITIVE LOGITS
    ichel
    0.11
     instead
    0.10
     quien
    0.10
    instead
    0.09
    ugs
    0.09
     stead
    0.09
    lex
    0.09
    udd
    0.09
     followed
    0.09
     Fro
    0.09
    Activations Density 1.687%

    No Known Activations