© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 50633
    Prev
    Next
    INDEX
    Explanations

    escalation and escalating tensions

    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
    cox
    -0.10
     blasted
    -0.10
    zial
    -0.10
    ucker
    -0.10
    itten
    -0.10
    inson
    -0.10
     ROT
    -0.10
    vig
    -0.10
    aukee
    -0.10
    aar
    -0.09
    POSITIVE LOGITS
     escal
    0.14
     tensions
    0.12
    ped
    0.11
     escalate
    0.11
     ramp
    0.11
     escalating
    0.10
     escalation
    0.10
     Ramp
    0.10
    ping
    0.10
     matters
    0.10
    Activations Density 0.021%

    No Known Activations