© 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. 7422
    Prev
    Next
    INDEX
    Explanations

    getting intense or overwhelmed

    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
     being
    -0.11
     calmly
    -0.10
     becoming
    -0.10
    aison
    -0.10
    being
    -0.09
     drunken
    -0.09
     thro
    -0.09
    idge
    -0.09
     angrily
    -0.09
    rack
    -0.08
    POSITIVE LOGITS
     excited
    0.11
     nostalgic
    0.11
     tired
    0.11
     nervous
    0.11
     Hav
    0.10
     comfortable
    0.10
     kle
    0.10
     mad
    0.10
     bored
    0.10
     needy
    0.10
    Activations Density 0.028%

    No Known Activations