© 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. 116502
    Prev
    Next
    INDEX
    Explanations

    celestial bodies orbiting

    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
     Chim
    -0.11
     nin
    -0.10
    untu
    -0.09
     Lama
    -0.09
     stamp
    -0.09
     ðŁij
    -0.09
     chim
    -0.09
     Salv
    -0.09
     patents
    -0.09
     Chop
    -0.09
    POSITIVE LOGITS
     orbit
    0.26
     orbits
    0.24
     orbital
    0.21
     rotation
    0.18
     revolving
    0.18
     rotates
    0.18
     Orbit
    0.18
    orbit
    0.17
     revolves
    0.17
     tilt
    0.17
    Activations Density 0.177%

    No Known Activations