© 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. 50867
    Prev
    Next
    INDEX
    Explanations

    internal compounds

    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
     lighter
    -0.12
     lighten
    -0.11
     cosmetic
    -0.11
     Electrical
    -0.11
     electrical
    -0.10
     electronics
    -0.10
     Morning
    -0.10
     Cosmetic
    -0.09
     cosmetics
    -0.09
     Electronics
    -0.09
    POSITIVE LOGITS
     internal
    0.20
     Internal
    0.18
     INTERNAL
    0.18
     interior
    0.18
     internals
    0.17
    åĨħ
    0.16
    Internal
    0.16
     internally
    0.16
     inside
    0.15
    internal
    0.15
    Activations Density 0.395%

    No Known Activations