© 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. 87768
    Prev
    Next
    INDEX
    Explanations

    likely file the How report

    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
    lian
    -0.10
     Showcase
    -0.10
    ailable
    -0.10
    (er
    -0.09
    avy
    -0.09
    uan
    -0.09
     Samar
    -0.09
     pops
    -0.08
    egin
    -0.08
    CLU
    -0.08
    POSITIVE LOGITS
     Meadows
    0.10
     Wilde
    0.10
    rido
    0.09
     Malk
    0.09
     spit
    0.09
     chromat
    0.09
    ç½®
    0.09
     besides
    0.09
     Rooney
    0.09
     Bain
    0.09
    Activations Density 0.001%

    No Known Activations