© 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. 47640
    Prev
    Next
    INDEX
    Explanations

    completing tasks and chores

    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
     Cav
    -0.11
    idia
    -0.10
     cliffs
    -0.10
     broad
    -0.10
     Cann
    -0.10
     Jog
    -0.09
    /styles
    -0.09
     cav
    -0.09
     Haram
    -0.09
     Gib
    -0.09
    POSITIVE LOGITS
     undone
    0.20
    /tasks
    0.18
     tasks
    0.17
     chores
    0.16
     Tasks
    0.13
     urgently
    0.13
    (tasks
    0.13
     mundane
    0.13
     priorities
    0.12
    tasks
    0.12
    Activations Density 0.110%

    No Known Activations