© 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. 25149
    Prev
    Next
    INDEX
    Explanations

    new instance or continuation

    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
     spender
    -0.11
    rede
    -0.11
    EPS
    -0.11
     hypocrisy
    -0.10
    zh
    -0.10
    ibold
    -0.10
    _OW
    -0.10
    aea
    -0.10
    andr
    -0.10
     Sus
    -0.10
    POSITIVE LOGITS
     round
    0.13
     bout
    0.12
     bouts
    0.10
     dose
    0.10
     iteration
    0.10
     set
    0.09
    -round
    0.09
     brief
    0.09
    /original
    0.08
     rounds
    0.08
    Activations Density 0.021%

    No Known Activations