© 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. 31478
    Prev
    Next
    INDEX
    Explanations

    taking actions

    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
    988
    -0.09
     brochure
    -0.09
     Merch
    -0.09
    irts
    -0.09
    aket
    -0.09
     circum
    -0.08
     disg
    -0.08
     tipped
    -0.08
     tem
    -0.08
     Picasso
    -0.08
    POSITIVE LOGITS
     steps
    0.11
     concepts
    0.10
     actions
    0.10
     дел
    0.09
     ps
    0.09
     vote
    0.09
    icast
    0.09
     votes
    0.09
    RON
    0.09
    Privacy
    0.09
    Activations Density 0.086%

    No Known Activations