© 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. 115914
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     hor
    -0.09
     laps
    -0.09
     Rew
    -0.08
     Rena
    -0.08
     hun
    -0.08
     Aud
    -0.08
     Profession
    -0.08
     Engagement
    -0.08
     Bing
    -0.08
    ãĥ¼ãĤ
    -0.08
    POSITIVE LOGITS
    xy
    0.09
    iglia
    0.09
    usty
    0.09
     stil
    0.08
    isti
    0.08
    ALSE
    0.08
     Highest
    0.08
     Ebay
    0.08
    robe
    0.08
     mest
    0.08
    Activations Density 0.000%

    No Known Activations