© 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. 113557
    Prev
    Next
    INDEX
    Explanations

    generally to

    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
    bed
    -0.10
    /class
    -0.09
    -type
    -0.09
     Abdullah
    -0.08
    els
    -0.08
    erm
    -0.08
    arb
    -0.08
    vod
    -0.08
    antly
    -0.08
    yst
    -0.08
    POSITIVE LOGITS
    ofil
    0.10
    leigh
    0.09
    .localized
    0.08
     Bog
    0.08
    Chunks
    0.08
    adle
    0.08
     Kendall
    0.08
    ounter
    0.08
    latin
    0.08
     Borg
    0.08
    Activations Density 0.007%

    No Known Activations