© 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. 88716
    Prev
    Next
    INDEX
    Explanations

    fear, surprise, 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
     impl
    -0.12
     Plain
    -0.09
     discrim
    -0.09
     refusal
    -0.09
    pain
    -0.09
     Pel
    -0.09
    ifu
    -0.08
     filib
    -0.08
     semantic
    -0.08
    alie
    -0.08
    POSITIVE LOGITS
     startled
    0.44
     scare
    0.32
     fright
    0.30
     scares
    0.29
     startling
    0.29
     scared
    0.26
     frightened
    0.25
     jump
    0.22
     sudden
    0.21
     surprise
    0.21
    Activations Density 0.050%

    No Known Activations