© 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. 46910
    Prev
    Next
    INDEX
    Explanations

    action identification

    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
     Baum
    -0.08
    views
    -0.08
     vis
    -0.07
     burdens
    -0.07
    loads
    -0.07
    apl
    -0.07
     disse
    -0.07
    baum
    -0.07
     cur
    -0.07
    ition
    -0.07
    POSITIVE LOGITS
     action
    0.27
    /action
    0.24
     Action
    0.23
    -action
    0.22
    .Action
    0.22
    -packed
    0.21
     ACTION
    0.21
    Action
    0.21
    (action
    0.20
    action
    0.19
    Activations Density 0.035%

    No Known Activations