© 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. 34078
    Prev
    Next
    INDEX
    Explanations

    calabresi

    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
    edback
    -0.09
     Bookmark
    -0.08
    arte
    -0.08
    еÑī
    -0.08
    efe
    -0.08
    otor
    -0.08
    uez
    -0.08
    idal
    -0.08
    quoise
    -0.08
    eci
    -0.08
    POSITIVE LOGITS
    vert
    0.15
    lear
    0.11
     lif
    0.10
    ipher
    0.10
    ving
    0.10
    o
    0.10
    tech
    0.09
    ahas
    0.09
    aire
    0.09
    lean
    0.09
    Activations Density 0.020%

    No Known Activations