© 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. 14263
    Prev
    Next
    INDEX
    Explanations

    numbers after question or part

    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
     &
    -0.11
     yr
    -0.11
     stmt
    -0.10
     pkt
    -0.10
    uin
    -0.08
     &↵
    -0.08
     Lt
    -0.08
     §
    -0.08
    DAY
    -0.08
     lagi
    -0.08
    POSITIVE LOGITS
     twenty
    0.30
     twelve
    0.29
     eighty
    0.28
     thirteen
    0.28
     fourteen
    0.28
     eighteen
    0.28
     ninety
    0.28
     thirty
    0.28
     forty
    0.28
     fifteen
    0.28
    Activations Density 0.391%

    No Known Activations