© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 112431
    Prev
    Next
    INDEX
    Explanations

    dense clusters, dwarf galaxies, age

    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
    Not in Any Lists

    No Comments

    Negative Logits
     perish
    -0.10
    adora
    -0.10
    ault
    -0.10
     feas
    -0.10
    atak
    -0.09
    518
    -0.09
    /style
    -0.09
     loaf
    -0.09
     guilt
    -0.09
     kata
    -0.09
    POSITIVE LOGITS
     resolved
    0.10
     unt
    0.09
     dens
    0.09
    dense
    0.09
     attenu
    0.09
     arms
    0.08
     Dense
    0.08
     dense
    0.08
     resolving
    0.08
    zag
    0.08
    Activations Density 0.011%

    No Known Activations