© 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. 15442
    Prev
    Next
    INDEX
    Explanations

    pretty much it or that's all

    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
     Tat
    -0.11
    (eval
    -0.10
     TG
    -0.10
     Geh
    -0.09
    793
    -0.09
    nn
    -0.09
     AQ
    -0.09
     prima
    -0.09
    mod
    -0.09
     fines
    -0.09
    POSITIVE LOGITS
     extent
    0.23
    extent
    0.17
     extents
    0.16
     limit
    0.13
    Extent
    0.13
     resemblance
    0.12
     similarities
    0.12
    _extent
    0.12
     similarity
    0.11
     ALL
    0.11
    Activations Density 0.073%

    No Known Activations