© 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. 13858
    Prev
    Next
    INDEX
    Explanations

    after a long time

    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
     reel
    -0.09
     Prem
    -0.09
    -java
    -0.08
     continually
    -0.08
     evac
    -0.08
    inia
    -0.08
     recl
    -0.08
    andle
    -0.08
     Ferr
    -0.08
     Cush
    -0.07
    POSITIVE LOGITS
     finally
    0.17
     eventually
    0.17
     Eventually
    0.17
     Finally
    0.16
    Eventually
    0.15
    Finally
    0.14
    finally
    0.14
     eventual
    0.13
     messages
    0.12
     Messages
    0.12
    Activations Density 0.009%

    No Known Activations