© 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. 27347
    Prev
    Next
    INDEX
    Explanations

    dates and times

    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
     hon
    -0.10
     Meer
    -0.09
     Bacon
    -0.09
    408
    -0.08
     sealed
    -0.08
     ter
    -0.08
     c
    -0.08
    coles
    -0.08
     ey
    -0.08
    gen
    -0.08
    POSITIVE LOGITS
     Organizer
    0.12
     organizer
    0.12
    picker
    0.11
     ugl
    0.10
    .IP
    0.10
     tomorrow
    0.10
     obed
    0.10
     finde
    0.10
     objc
    0.10
     procur
    0.10
    Activations Density 0.025%

    No Known Activations