© 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. 5799
    Prev
    Next
    INDEX
    Explanations

    task completion

    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
     Flesh
    -0.12
     deactivated
    -0.11
    Inactive
    -0.11
     Rescue
    -0.10
    dere
    -0.10
     Crazy
    -0.10
     Tin
    -0.10
     blat
    -0.10
     Activate
    -0.09
    restricted
    -0.09
    POSITIVE LOGITS
     completed
    0.29
     completion
    0.28
     quality
    0.25
     finished
    0.24
     Completed
    0.24
     Completion
    0.23
    completion
    0.22
     redo
    0.22
    completed
    0.21
     done
    0.21
    Activations Density 0.215%

    No Known Activations