© 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. 26836
    Prev
    Next
    INDEX
    Explanations

    percentage of voters

    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
     McD
    -0.09
     strand
    -0.09
     owed
    -0.09
     Swarm
    -0.09
    elay
    -0.08
    piel
    -0.08
     wax
    -0.08
     devis
    -0.08
     McMahon
    -0.08
    vis
    -0.08
    POSITIVE LOGITS
     polled
    0.11
    essa
    0.10
     gen
    0.09
    #elif
    0.09
     DK
    0.09
     hookup
    0.09
    认
    0.08
     surveyed
    0.08
     BK
    0.08
     stricter
    0.08
    Activations Density 0.116%

    No Known Activations