© 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. 29557
    Prev
    Next
    INDEX
    Explanations

    ending punctuation followed by "the"

    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
    isu
    -0.12
    [js
    -0.12
    orta
    -0.10
     jealous
    -0.10
     ventil
    -0.10
     scand
    -0.10
    hel
    -0.10
    lea
    -0.10
     expo
    -0.09
    (IB
    -0.09
    POSITIVE LOGITS
    ...</
    0.09
     therein
    0.09
     Alias
    0.08
     bubb
    0.08
    ...
    0.08
    ).</
    0.08
     lo
    0.08
     bubble
    0.08
     Em
    0.08
     Stub
    0.08
    Activations Density 0.010%

    No Known Activations