© 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. 7013
    Prev
    Next
    INDEX
    Explanations

    escalate to more serious

    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
     tantal
    -0.10
    -prev
    -0.10
     apl
    -0.10
     soaking
    -0.10
     absent
    -0.10
     suscept
    -0.10
     Sark
    -0.10
    rick
    -0.09
    -layout
    -0.09
    -placeholder
    -0.09
    POSITIVE LOGITS
     escalate
    0.28
     escalated
    0.27
     escal
    0.25
     spir
    0.24
     escalating
    0.23
    escal
    0.22
     escalation
    0.22
     spiral
    0.20
     uncont
    0.18
     Esc
    0.17
    Activations Density 0.094%

    No Known Activations