© 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. 87629
    Prev
    Next
    INDEX
    Explanations

    driving vehicles

    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
    uger
    -0.11
    DDD
    -0.11
    aldi
    -0.11
    woke
    -0.11
    achel
    -0.10
    /string
    -0.10
     Katz
    -0.10
     Kore
    -0.10
     XS
    -0.10
    omp
    -0.10
    POSITIVE LOGITS
     nail
    0.13
     stakes
    0.12
     nails
    0.11
     reck
    0.11
     Nail
    0.10
     wedge
    0.09
    umba
    0.09
    ấ
    0.09
     home
    0.09
     stake
    0.08
    Activations Density 0.021%

    No Known Activations