© 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. 31030
    Prev
    Next
    INDEX
    Explanations

    underneath, visible, or behind

    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
     visible
    -0.11
     Visible
    -0.11
    Visible
    -0.10
     visibility
    -0.09
     encounter
    -0.09
     invis
    -0.09
    _visible
    -0.09
     intoxicated
    -0.09
     Bry
    -0.09
     goodies
    -0.09
    POSITIVE LOGITS
     beneath
    0.14
     underneath
    0.12
     behind
    0.11
     BELOW
    0.10
     amongst
    0.10
     underside
    0.10
     below
    0.10
     along
    0.10
     hovering
    0.09
     outline
    0.09
    Activations Density 0.066%

    No Known Activations