© 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. 16017
    Prev
    Next
    INDEX
    Explanations

    numbers following "just"

    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
    anie
    -0.12
    whole
    -0.11
     whole
    -0.10
    Whole
    -0.10
     suit
    -0.10
    anon
    -0.10
     Whole
    -0.10
     gan
    -0.10
     larger
    -0.10
     boasted
    -0.09
    POSITIVE LOGITS
     half
    0.10
     halves
    0.09
    half
    0.09
    _partial
    0.09
     incomplete
    0.09
     shortened
    0.08
     Bronze
    0.08
     Airlines
    0.08
    partial
    0.08
    rok
    0.08
    Activations Density 0.862%

    No Known Activations