© 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. 92475
    Prev
    Next
    INDEX
    Explanations

    smiles, writing, code, medical, ARC

    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
     smile
    -0.13
     smiling
    -0.12
     blinking
    -0.12
     flashes
    -0.11
     smiles
    -0.11
     grin
    -0.10
     smiled
    -0.10
    nage
    -0.09
     gn
    -0.09
     funnel
    -0.09
    POSITIVE LOGITS
     Frozen
    0.12
     Quar
    0.11
     Frid
    0.11
    ections
    0.11
    orners
    0.11
     corners
    0.11
    mus
    0.10
     Fal
    0.10
     Pain
    0.10
    -wrapper
    0.10
    Activations Density 0.003%

    No Known Activations