© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 46100
    Prev
    Next
    INDEX
    Explanations

    planets and astronomy-related terms

    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
    Negative Logits
    /link
    -0.09
     Viv
    -0.09
     hast
    -0.09
    ainless
    -0.09
     fool
    -0.08
     Suitable
    -0.08
     haste
    -0.08
    gart
    -0.08
    lhs
    -0.08
    hc
    -0.08
    POSITIVE LOGITS
    /star
    0.14
     Astronomy
    0.13
     orbit
    0.13
     astronauts
    0.13
     astronomers
    0.13
    shine
    0.13
     astro
    0.12
    esimal
    0.12
     Jupiter
    0.12
     Telescope
    0.12
    Activations Density 0.205%

    No Known Activations