© 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. 89426
    Prev
    Next
    INDEX
    Explanations

    under pressure or stressed

    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
    onet
    -0.13
    apan
    -0.12
    -now
    -0.11
    atak
    -0.11
    ailles
    -0.11
    (inst
    -0.11
     redund
    -0.11
     Chunk
    -0.10
    GRAM
    -0.10
     Abr
    -0.10
    POSITIVE LOGITS
     lately
    0.13
     elsewhere
    0.09
     due
    0.09
     after
    0.09
     rn
    0.08
    iti
    0.08
     fool
    0.08
     owing
    0.08
     genuinely
    0.08
     needing
    0.08
    Activations Density 0.047%

    No Known Activations