© 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. 92414
    Prev
    Next
    INDEX
    Explanations

    not yet completely

    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
     EXCEPTION
    -0.10
     except
    -0.09
     anymore
    -0.09
    erring
    -0.09
    und
    -0.09
     overst
    -0.08
     Ore
    -0.08
     nun
    -0.08
     underst
    -0.08
     prem
    -0.08
    POSITIVE LOGITS
     completely
    0.38
     Completely
    0.32
     entirely
    0.29
     totally
    0.28
     COMPLETE
    0.25
     wholly
    0.24
     permanently
    0.23
     Totally
    0.21
     complet
    0.20
     totalement
    0.20
    Activations Density 0.163%

    No Known Activations