© 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. 90411
    Prev
    Next
    INDEX
    Explanations

    center or central

    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
    arda
    -0.09
    Perm
    -0.09
     companion
    -0.09
    icles
    -0.09
     accomp
    -0.09
     additional
    -0.09
     flank
    -0.09
    ear
    -0.08
     skins
    -0.08
     scraped
    -0.08
    POSITIVE LOGITS
     center
    0.47
     central
    0.45
     centre
    0.43
     centrally
    0.40
     centerpiece
    0.35
    -center
    0.35
     centr
    0.35
    central
    0.34
    center
    0.34
    centre
    0.34
    Activations Density 0.798%

    No Known Activations