© 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. 31827
    Prev
    Next
    INDEX
    Explanations

    perinatal outcomes

    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
    /as
    -0.09
    -induced
    -0.09
    isted
    -0.09
    /single
    -0.08
    Nom
    -0.08
     Bonnie
    -0.08
    -turned
    -0.08
    -made
    -0.08
    .Management
    -0.08
    -generated
    -0.07
    POSITIVE LOGITS
     unsur
    0.09
    udo
    0.09
    -worthy
    0.09
    :class
    0.09
     Quint
    0.09
     maker
    0.09
    aina
    0.09
    /error
    0.08
     Äijược
    0.08
    -building
    0.08
    Activations Density 5.434%

    No Known Activations