© 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. 47770
    Prev
    Next
    INDEX
    Explanations

    technical or domain specific nouns

    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
    ifo
    -0.10
    sole
    -0.10
     seri
    -0.09
     Painter
    -0.09
     bew
    -0.09
    argo
    -0.09
    nen
    -0.09
    kie
    -0.09
     hinges
    -0.09
    pagesize
    -0.09
    POSITIVE LOGITS
     accessor
    0.08
    uble
    0.08
    /non
    0.08
    -related
    0.08
     Tal
    0.08
    097
    0.07
     Burg
    0.07
    idente
    0.07
    burg
    0.07
     fle
    0.07
    Activations Density 0.628%

    No Known Activations