© 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. 31004
    Prev
    Next
    INDEX
    Explanations

    panic, scrambled, rushed

    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
     sigh
    -0.15
     wink
    -0.14
     sighed
    -0.14
     smile
    -0.13
     Smile
    -0.13
     smiling
    -0.13
     smirk
    -0.12
     smiles
    -0.11
     smiled
    -0.11
     Britt
    -0.11
    POSITIVE LOGITS
     panic
    0.16
     scrambled
    0.16
     scramble
    0.15
     panicked
    0.15
     frantic
    0.15
     scram
    0.14
     rushed
    0.13
     scrambling
    0.13
     shri
    0.13
     alarmed
    0.13
    Activations Density 0.042%

    No Known Activations