© 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. 18645
    Prev
    Next
    INDEX
    Explanations

    physical parts of objects, bodies, or structures

    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
    uyo
    -0.08
     Rom
    -0.08
    erea
    -0.07
     States
    -0.07
     Christopher
    -0.07
     colleg
    -0.07
    aine
    -0.07
     refresh
    -0.06
     delegation
    -0.06
     unc
    -0.06
    POSITIVE LOGITS
     tissues
    0.12
    anh
    0.12
    oints
    0.12
     taraf
    0.12
     Maxwell
    0.11
     underneath
    0.11
    ToDevice
    0.11
    ĶĦ
    0.11
     flesh
    0.11
    fdc
    0.11
    Activations Density 0.851%

    No Known Activations