© 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. 15303
    Prev
    Next
    INDEX
    Explanations

    shocked or confused reactions

    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
     amusing
    -0.12
     loc
    -0.10
     hopefully
    -0.10
     es
    -0.10
     Neh
    -0.09
     Hopefully
    -0.09
     eventual
    -0.09
    una
    -0.09
     entertaining
    -0.09
    ovic
    -0.09
    POSITIVE LOGITS
     bewild
    0.15
     shocked
    0.15
     baff
    0.15
     dazz
    0.15
     shock
    0.14
     stunned
    0.14
     panic
    0.14
     confused
    0.13
     instinct
    0.13
     Panic
    0.13
    Activations Density 0.035%

    No Known Activations