© 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. 31022
    Prev
    Next
    INDEX
    Explanations

    engage in activities

    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
    rer
    -0.12
     Tears
    -0.11
    omic
    -0.11
    reds
    -0.10
    irs
    -0.10
    ato
    -0.10
    ople
    -0.10
    ician
    -0.10
    reu
    -0.10
    licant
    -0.10
    POSITIVE LOGITS
     activities
    0.09
     in
    0.09
     Activities
    0.08
     drift
    0.08
     decl
    0.08
     Norman
    0.07
     dyn
    0.07
     deed
    0.07
     readers
    0.07
     Clifford
    0.07
    Activations Density 0.002%

    No Known Activations