© 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. 6155
    Prev
    Next
    INDEX
    Explanations

    non woven, Buddhism, after

    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
    !--
    -0.11
    datal
    -0.09
     bog
    -0.09
     mid
    -0.08
    ilik
    -0.08
    idata
    -0.08
     anc
    -0.08
     CENT
    -0.08
     rav
    -0.08
     mistaken
    -0.08
    POSITIVE LOGITS
    (att
    0.09
    iges
    0.09
     Rope
    0.09
    gia
    0.09
    ë£
    0.09
     painting
    0.09
     kidnapped
    0.08
    Ñĥж
    0.08
    ÙĴ
    0.08
     Rings
    0.08
    Activations Density 0.002%

    No Known Activations