© 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. 16397
    Prev
    Next
    INDEX
    Explanations

    rest of everything

    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
     another
    -0.11
    another
    -0.11
     additional
    -0.09
     additionally
    -0.09
    zano
    -0.09
     Another
    -0.08
    enn
    -0.08
     wil
    -0.08
    Another
    -0.08
     Cay
    -0.08
    POSITIVE LOGITS
     rest
    0.47
     everything
    0.36
    rest
    0.33
    everything
    0.32
     Everything
    0.32
     remainder
    0.31
    Everything
    0.30
     Rest
    0.29
    Rest
    0.27
    (rest
    0.25
    Activations Density 0.312%

    No Known Activations