© 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. 13949
    Prev
    Next
    INDEX
    Explanations

    variety of types and attributes

    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
    iram
    -0.09
     dens
    -0.08
     indiv
    -0.08
     divisible
    -0.08
     Vers
    -0.08
    oeff
    -0.08
     epid
    -0.08
     encodeURIComponent
    -0.08
     balanced
    -0.08
     peeled
    -0.08
    POSITIVE LOGITS
     colors
    0.22
     shapes
    0.22
     sizes
    0.21
     colours
    0.21
     styles
    0.20
     brands
    0.19
     size
    0.18
     shape
    0.17
     color
    0.17
     style
    0.16
    Activations Density 0.256%

    No Known Activations