© 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. 29790
    Prev
    Next
    INDEX
    Explanations

    floating or hovering object

    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
     downhill
    -0.12
    aye
    -0.10
    ache
    -0.10
     splash
    -0.09
    SON
    -0.09
     dove
    -0.09
     collapses
    -0.09
     bah
    -0.09
     disgu
    -0.08
     enlisted
    -0.08
    POSITIVE LOGITS
    -floating
    0.25
     floating
    0.22
     suspended
    0.21
     lev
    0.21
     hovering
    0.21
     hover
    0.20
     Floating
    0.20
     hovered
    0.19
     suspension
    0.19
     suspend
    0.19
    Activations Density 0.152%

    No Known Activations