© 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. 31411
    Prev
    Next
    INDEX
    Explanations

    holder, bracket, adapter, pouch, rest, device, retainer

    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
    okus
    -0.12
     Walton
    -0.12
     Sheldon
    -0.12
    illas
    -0.12
    rikes
    -0.12
     Shaft
    -0.11
     VARIABLE
    -0.11
    .wr
    -0.11
    patches
    -0.11
    allon
    -0.11
    POSITIVE LOGITS
     attached
    0.12
     attachment
    0.11
     installed
    0.08
     attachments
    0.08
     assembly
    0.08
     device
    0.08
     integrated
    0.08
     fitted
    0.08
    attached
    0.07
     containing
    0.07
    Activations Density 0.399%

    No Known Activations