© 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. 34110
    Prev
    Next
    INDEX
    Explanations

    end of sentence/thought

    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
     reint
    -0.12
    .initState
    -0.12
     incon
    -0.11
     initially
    -0.11
     immediately
    -0.11
     readiness
    -0.11
     turf
    -0.11
     instantly
    -0.11
    ovel
    -0.11
    318
    -0.11
    POSITIVE LOGITS
     Again
    0.17
     again
    0.16
    again
    0.15
    Again
    0.14
     now
    0.12
     Finally
    0.10
     dit
    0.10
     increasingly
    0.10
    now
    0.10
     finally
    0.09
    Activations Density 0.025%

    No Known Activations