© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 5491
    Prev
    Next
    INDEX
    Explanations

    opening and closing mechanisms

    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
     coco
    -0.11
    TypeEnum
    -0.10
     sacks
    -0.10
    iked
    -0.10
     dehydration
    -0.10
     emptied
    -0.10
     unordered
    -0.09
     melted
    -0.09
     swept
    -0.09
     containers
    -0.09
    POSITIVE LOGITS
     cork
    0.15
     Cork
    0.12
     punct
    0.12
    ignon
    0.12
     extractor
    0.11
     inverted
    0.10
     Vin
    0.10
     extraction
    0.10
     upside
    0.10
    aux
    0.09
    Activations Density 0.042%

    No Known Activations