© 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. 89044
    Prev
    Next
    INDEX
    Explanations

    flying and airspace

    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
     walking
    -0.13
     walked
    -0.13
     walk
    -0.13
     Walking
    -0.13
     walks
    -0.13
     standing
    -0.11
    Walking
    -0.11
     Aub
    -0.11
     topp
    -0.11
     todd
    -0.11
    POSITIVE LOGITS
     altitude
    0.22
     airspace
    0.20
     clouds
    0.18
     cir
    0.17
    altitude
    0.16
     alt
    0.15
     cruising
    0.15
     radar
    0.14
     Alt
    0.14
     skies
    0.14
    Activations Density 0.399%

    No Known Activations