© 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. 114217
    Prev
    Next
    INDEX
    Explanations

    network congestion

    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
    394
    -0.08
     There
    -0.08
    287
    -0.08
     Uses
    -0.08
     there
    -0.07
    illo
    -0.07
     Accountability
    -0.07
    There
    -0.07
     bypass
    -0.07
    ardin
    -0.07
    POSITIVE LOGITS
     lack
    0.25
     presence
    0.22
     proximity
    0.20
     Lack
    0.18
     combination
    0.18
    presence
    0.18
     absence
    0.18
     inability
    0.17
     actions
    0.16
     Presence
    0.15
    Activations Density 0.984%

    No Known Activations