© 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. 5876
    Prev
    Next
    INDEX
    Explanations

    our or we

    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
     reportedly
    -0.12
     hers
    -0.09
     presumably
    -0.09
     oneself
    -0.09
     himself
    -0.08
     him
    -0.08
    him
    -0.08
     apparently
    -0.08
     "..
    -0.08
     THEIR
    -0.08
    POSITIVE LOGITS
     our
    0.71
    Our
    0.59
     Our
    0.58
     ours
    0.55
    our
    0.53
    .Our
    0.51
    æĪij们
    0.50
     OUR
    0.49
     we
    0.45
     ourselves
    0.44
    Activations Density 2.022%

    No Known Activations