© 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. 49938
    Prev
    Next
    INDEX
    Explanations

    arrival at destination

    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
     reput
    -0.10
     malt
    -0.09
     sel
    -0.09
     Polo
    -0.09
     upt
    -0.09
     jury
    -0.09
     boyc
    -0.08
     suing
    -0.08
    aba
    -0.08
     af
    -0.08
    POSITIVE LOGITS
     landing
    0.22
     landed
    0.21
     cruising
    0.19
     Landing
    0.19
     land
    0.19
     docking
    0.18
     descent
    0.17
     arrival
    0.17
     acceleration
    0.16
    landing
    0.16
    Activations Density 0.062%

    No Known Activations