© 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. 13902
    Prev
    Next
    INDEX
    Explanations

    claim that it leads to

    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
    ustin
    -0.12
    isque
    -0.11
    amba
    -0.10
    orate
    -0.10
     afterward
    -0.10
    quota
    -0.10
     rebound
    -0.10
     bacon
    -0.10
    amu
    -0.09
    uteur
    -0.09
    POSITIVE LOGITS
     dow
    0.08
     sims
    0.08
    lan
    0.08
     chaining
    0.08
     boasted
    0.08
    ship
    0.08
    ddy
    0.08
     Weaver
    0.08
     Schiff
    0.08
     dec
    0.08
    Activations Density 0.001%

    No Known Activations