© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 16281
    Prev
    Next
    INDEX
    Explanations

    expressing surprise or shock

    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
     Ebony
    -0.12
    füg
    -0.11
    lian
    -0.11
    ibri
    -0.11
    apper
    -0.11
     nn
    -0.11
     Vu
    -0.11
    SOR
    -0.11
    altar
    -0.11
    enso
    -0.11
    POSITIVE LOGITS
     anyone
    0.17
     anybody
    0.14
     surprised
    0.14
     hasn
    0.12
     Anyone
    0.12
     hadn
    0.11
     Sur
    0.11
     surprising
    0.11
     haven
    0.10
    -sur
    0.10
    Activations Density 0.021%

    No Known Activations