© 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. 17048
    Prev
    Next
    INDEX
    Explanations

    Mars, Martian, rover

    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
     Nashville
    -0.09
     mint
    -0.09
     Vib
    -0.09
     rainbow
    -0.09
     lum
    -0.09
     Vy
    -0.09
     Dil
    -0.08
     Birmingham
    -0.08
     Blackburn
    -0.08
    ç©
    -0.08
    POSITIVE LOGITS
     Martian
    0.44
     Mars
    0.43
     mars
    0.37
     mart
    0.31
    mars
    0.30
    Mart
    0.30
     Mart
    0.28
    -Mart
    0.27
     Martinez
    0.23
     rover
    0.23
    Activations Density 0.605%

    No Known Activations