© 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. 111623
    Prev
    Next
    INDEX
    Explanations

    units of time, weight, or length

    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
     Colleg
    -0.07
     creep
    -0.07
     Fat
    -0.07
    irit
    -0.07
     colon
    -0.06
    Ñģп
    -0.06
    pect
    -0.06
    MASTER
    -0.06
     hic
    -0.06
     conduct
    -0.06
    POSITIVE LOGITS
    gu
    0.11
    zig
    0.11
     Pru
    0.11
     prepaid
    0.11
    Dyn
    0.10
    -paid
    0.10
    ahu
    0.10
    /sources
    0.10
    wend
    0.10
    Supported
    0.10
    Activations Density 0.018%

    No Known Activations