© 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. 117547
    Prev
    Next
    INDEX
    Explanations

    states of function or malfunction

    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
    yo
    -0.10
    anno
    -0.10
    (PR
    -0.10
     chois
    -0.10
    icum
    -0.10
    Protected
    -0.10
    aks
    -0.10
     unprotected
    -0.09
     jig
    -0.09
     buffered
    -0.09
    POSITIVE LOGITS
     allowing
    0.09
    indic
    0.08
     overtime
    0.08
    aniu
    0.08
     Riy
    0.08
    uber
    0.08
     aiding
    0.08
     Rand
    0.08
    'b
    0.08
     Bris
    0.08
    Activations Density 0.572%

    No Known Activations