© 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. 3622
    Prev
    Next
    INDEX
    Explanations

    traffic reports, water purification, wine pairing, voltage limits, computing device, lunar phase, secure communication, crime, that

    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
    
    -0.09
     badge
    -0.09
     Scor
    -0.08
     Coast
    -0.08
     undefined
    -0.07
    mil
    -0.07
     lash
    -0.07
     commenter
    -0.07
     Coastal
    -0.07
     coast
    -0.07
    POSITIVE LOGITS
    !,↵
    0.10
     Trom
    0.10
     ==↵
    0.10
    !;↵
    0.10
     redirects
    0.09
     fiat
    0.09
    hurst
    0.09
     xv
    0.09
     .....
    0.09
    åĭ
    0.09
    Activations Density 0.897%

    No Known Activations