© 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. 27160
    Prev
    Next
    INDEX
    Explanations

    protection and security

    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
     blindly
    -0.09
     Spa
    -0.09
     Retreat
    -0.09
     dangers
    -0.08
     _(
    -0.08
     Chains
    -0.08
     optional
    -0.08
    lying
    -0.08
     admittedly
    -0.08
     headlines
    -0.08
    POSITIVE LOGITS
     Protected
    0.12
     protected
    0.11
     Markus
    0.10
     Sit
    0.10
    Protected
    0.10
     protections
    0.09
     Newton
    0.09
     observe
    0.09
    tight
    0.09
     Strong
    0.09
    Activations Density 0.005%

    No Known Activations