© 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. 46097
    Prev
    Next
    INDEX
    Explanations

    fence and enclosure structures

    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
    spaces
    -0.11
    sets
    -0.11
    iem
    -0.10
    spent
    -0.10
     bedrooms
    -0.10
     Steering
    -0.10
     Trom
    -0.09
    akh
    -0.09
    nock
    -0.09
    (Module
    -0.09
    POSITIVE LOGITS
     fence
    0.16
     Fence
    0.14
     fences
    0.12
     fencing
    0.12
     surrounding
    0.12
    post
    0.10
    _fence
    0.10
     enclosing
    0.10
    esan
    0.10
    odont
    0.10
    Activations Density 0.029%

    No Known Activations