© 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. 29030
    Prev
    Next
    INDEX
    Explanations

    perforated holes or openings

    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
     swelling
    -0.11
     EDGE
    -0.10
    quo
    -0.10
     Cout
    -0.10
     filling
    -0.10
     slack
    -0.10
     pry
    -0.10
     tastes
    -0.10
    actoring
    -0.09
     sleeper
    -0.09
    POSITIVE LOGITS
    allow
    0.11
     holes
    0.11
     permitting
    0.09
     allowing
    0.09
    sie
    0.09
     aer
    0.09
    permit
    0.09
     drilled
    0.09
     Arguments
    0.09
     hole
    0.09
    Activations Density 0.275%

    No Known Activations