© 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. 13882
    Prev
    Next
    INDEX
    Explanations

    but, rather, more

    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
    853
    -0.09
    Attrs
    -0.08
     dok
    -0.08
     Property
    -0.08
    atives
    -0.08
     coraz
    -0.08
     rods
    -0.08
     Altern
    -0.08
     Wid
    -0.08
     bat
    -0.08
    POSITIVE LOGITS
     simply
    0.23
    Simply
    0.17
     Simply
    0.14
     simplement
    0.14
     merely
    0.14
     rather
    0.12
     Rather
    0.11
    Rather
    0.11
    pha
    0.11
    rather
    0.10
    Activations Density 0.138%

    No Known Activations