© 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. 46178
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    anch
    -0.10
    actoring
    -0.10
    ovo
    -0.10
     sach
    -0.09
    anna
    -0.09
     Prof
    -0.09
    xac
    -0.09
    /report
    -0.09
     Tent
    -0.08
     Lesser
    -0.08
    POSITIVE LOGITS
     Kushner
    0.10
     Butler
    0.10
     swear
    0.09
     swore
    0.09
     Randall
    0.09
    ammo
    0.09
     да
    0.09
    erus
    0.08
    iffe
    0.08
     :↵
    0.08
    Activations Density 0.000%

    No Known Activations