© 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. 45971
    Prev
    Next
    INDEX
    Explanations

    compare or comparisons

    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
     difference
    -0.11
     Difference
    -0.11
    Difference
    -0.10
     purs
    -0.09
    difference
    -0.08
    icker
    -0.08
    iba
    -0.08
     xen
    -0.08
     Hib
    -0.08
    vak
    -0.08
    POSITIVE LOGITS
     unfavor
    0.25
     comparisons
    0.25
     compares
    0.22
     comparison
    0.22
     compare
    0.21
     comparing
    0.20
     Comparison
    0.18
    compare
    0.18
    .compare
    0.17
    comparison
    0.17
    Activations Density 0.090%

    No Known Activations