© 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. 112516
    Prev
    Next
    INDEX
    Explanations

    sudden shock 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
    ichel
    -0.12
     generously
    -0.11
     naturally
    -0.10
    wis
    -0.10
     praises
    -0.10
     loosely
    -0.10
     rampant
    -0.10
     voluntarily
    -0.10
    -errors
    -0.10
     rave
    -0.10
    POSITIVE LOGITS
     shock
    0.32
     startled
    0.26
     surprise
    0.25
     startling
    0.25
     shocking
    0.25
     shocks
    0.24
     Shock
    0.24
     shocked
    0.23
     sudden
    0.22
    Shock
    0.21
    Activations Density 0.057%

    No Known Activations