© 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. 26065
    Prev
    Next
    INDEX
    Explanations

    religious or cultural figures

    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
    illy
    -0.10
     Hentai
    -0.10
    cut
    -0.10
     creat
    -0.09
    tone
    -0.09
     newsp
    -0.09
     tro
    -0.09
     Male
    -0.09
     utterly
    -0.09
    /packages
    -0.09
    POSITIVE LOGITS
     neighbor
    0.10
    yi
    0.10
     neighbour
    0.10
    们
    0.10
     Raymond
    0.10
     whom
    0.09
    _neighbor
    0.09
     sare
    0.09
     neighbors
    0.09
    532
    0.09
    Activations Density 0.006%

    No Known Activations