© 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. 92097
    Prev
    Next
    INDEX
    Explanations

    guard or perimeter defense

    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
    GOR
    -0.10
    igraph
    -0.10
    enco
    -0.09
     palms
    -0.09
    -eff
    -0.09
    633
    -0.09
    ibilit
    -0.09
    scape
    -0.09
    orgen
    -0.09
     Cler
    -0.09
    POSITIVE LOGITS
     gate
    0.16
     gates
    0.16
     against
    0.15
     perimeter
    0.13
     Against
    0.13
     closely
    0.12
    against
    0.12
     entrance
    0.12
    Against
    0.12
     entrances
    0.12
    Activations Density 0.107%

    No Known Activations