© 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. 32407
    Prev
    Next
    INDEX
    Explanations

    security and protection measures

    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
     defended
    -0.12
     healing
    -0.11
     recre
    -0.11
     healed
    -0.10
    clin
    -0.10
     unle
    -0.10
     conservation
    -0.10
     insulated
    -0.10
     fertil
    -0.10
    enge
    -0.09
    POSITIVE LOGITS
    /mit
    0.15
     mandated
    0.13
     effectiveness
    0.12
     proactive
    0.12
     inadequate
    0.12
     ineffective
    0.11
     adequ
    0.11
     dracon
    0.11
     practiced
    0.11
     measures
    0.10
    Activations Density 0.980%

    No Known Activations