© 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. 46244
    Prev
    Next
    INDEX
    Explanations

    sentence endings followed by capitalized words

    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
    )did
    -0.11
     interracial
    -0.10
     Roy
    -0.10
    /ca
    -0.10
    OPS
    -0.10
     forg
    -0.10
    icio
    -0.10
     wr
    -0.09
    ç«ł
    -0.09
     fore
    -0.09
    POSITIVE LOGITS
    atha
    0.08
     bur
    0.08
    ook
    0.08
     orm
    0.08
    amus
    0.07
    oste
    0.07
     bob
    0.07
     Globals
    0.07
    kat
    0.07
    ukt
    0.07
    Activations Density 0.090%

    No Known Activations