© 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. 117341
    Prev
    Next
    INDEX
    Explanations

    cornerstone, staple, pillar, anchor

    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
    JB
    -0.08
    amac
    -0.08
    robe
    -0.08
    ugu
    -0.08
     experts
    -0.07
    msp
    -0.07
     Kov
    -0.07
    för
    -0.07
     Inner
    -0.07
    ogn
    -0.07
    POSITIVE LOGITS
     pillar
    0.18
     among
    0.16
     amongst
    0.14
     cornerstone
    0.13
     pillars
    0.13
     backbone
    0.13
    kest
    0.13
    among
    0.12
     anchor
    0.12
    wart
    0.12
    Activations Density 0.144%

    No Known Activations