© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 90654
    Prev
    Next
    INDEX
    Explanations

    performing actions or tasks

    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
    osto
    -0.11
    ernes
    -0.11
    uzzi
    -0.10
    plevel
    -0.10
    fan
    -0.10
    osite
    -0.10
     clouds
    -0.10
    ansk
    -0.09
    UCT
    -0.09
    DONE
    -0.09
    POSITIVE LOGITS
     duties
    0.34
     tasks
    0.28
     functions
    0.23
     Dut
    0.21
     acts
    0.20
     Tasks
    0.20
     task
    0.20
     duty
    0.19
     actions
    0.19
    tasks
    0.19
    Activations Density 0.202%

    No Known Activations