© 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. 28960
    Prev
    Next
    INDEX
    Explanations

    earthquake magnitude

    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
     flam
    -0.11
     shred
    -0.10
     burn
    -0.10
     stump
    -0.10
     infl
    -0.10
     burned
    -0.10
     mental
    -0.10
     Flam
    -0.10
     ros
    -0.10
     autor
    -0.10
    POSITIVE LOGITS
     earthquake
    0.48
     earthquakes
    0.44
     seismic
    0.40
     quake
    0.39
     earthqu
    0.38
     trem
    0.30
    quake
    0.29
     shaking
    0.26
     aft
    0.26
    earth
    0.24
    Activations Density 0.322%

    No Known Activations