© 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. 5703
    Prev
    Next
    INDEX
    Explanations

    delays and complexity

    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
    aura
    -0.10
    ishi
    -0.09
     ephem
    -0.09
    ahun
    -0.09
     hawk
    -0.09
    aria
    -0.09
    /mac
    -0.09
     Ari
    -0.09
    ará
    -0.09
    ware
    -0.09
    POSITIVE LOGITS
     slow
    0.19
     slower
    0.18
     slowed
    0.17
    slow
    0.16
     Slow
    0.15
     complicated
    0.14
    Slow
    0.14
     unfore
    0.14
     complexity
    0.13
     slows
    0.13
    Activations Density 0.231%

    No Known Activations