© 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. 116509
    Prev
    Next
    INDEX
    Explanations

    spatial separation

    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
    osen
    -0.09
     fell
    -0.09
     shores
    -0.09
     hotline
    -0.09
     beware
    -0.09
     adaptive
    -0.08
     narciss
    -0.08
     delayed
    -0.08
    izons
    -0.08
    atte
    -0.08
    POSITIVE LOGITS
     two
    0.13
    两
    0.13
     between
    0.11
    between
    0.11
    two
    0.11
    both
    0.11
     both
    0.11
     torn
    0.10
     beiden
    0.10
    -two
    0.10
    Activations Density 0.009%

    No Known Activations