© 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. 14434
    Prev
    Next
    INDEX
    Explanations

    probably the

    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
    eral
    -0.10
    ograd
    -0.09
     dicho
    -0.09
    opot
    -0.09
    ee
    -0.09
     criter
    -0.09
    Ops
    -0.09
     ach
    -0.08
    elden
    -0.08
    entar
    -0.08
    POSITIVE LOGITS
     more
    0.13
     most
    0.11
     fewer
    0.11
     inevitable
    0.11
     deserve
    0.11
     inevitably
    0.10
     worth
    0.10
     ranks
    0.10
     best
    0.10
     less
    0.10
    Activations Density 0.033%

    No Known Activations