© 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. 28386
    Prev
    Next
    INDEX
    Explanations

    aliens and space technology

    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
     Coach
    -0.08
     inline
    -0.08
     Blind
    -0.08
     pert
    -0.08
     Wilkinson
    -0.08
     Candle
    -0.08
     unpack
    -0.07
     Flow
    -0.07
     Pert
    -0.07
     Pawn
    -0.07
    POSITIVE LOGITS
     spaceship
    0.33
     aliens
    0.27
     spacecraft
    0.26
     alien
    0.25
     planet
    0.23
     Martian
    0.22
     astronauts
    0.22
     futuristic
    0.22
     space
    0.22
     planets
    0.21
    Activations Density 0.152%

    No Known Activations