© 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. 28737
    Prev
    Next
    INDEX
    Explanations

    in the news

    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
    overe
    -0.10
    edge
    -0.09
     coast
    -0.09
     doorstep
    -0.09
    uo
    -0.08
    inox
    -0.08
     shelf
    -0.08
    olume
    -0.08
     shores
    -0.08
    icing
    -0.08
    POSITIVE LOGITS
     midst
    0.35
     meantime
    0.29
     hopes
    0.26
     absence
    0.24
     wake
    0.23
     vicinity
    0.21
     evenings
    0.20
     meanwhile
    0.19
     middle
    0.19
     mornings
    0.19
    Activations Density 0.674%

    No Known Activations