© 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. 15763
    Prev
    Next
    INDEX
    Explanations

    preliminary scientific findings

    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
     oft
    -0.11
     inev
    -0.11
    ADR
    -0.10
     Directorate
    -0.10
    auen
    -0.10
     inevitable
    -0.10
     Rut
    -0.10
     passé
    -0.10
    eldom
    -0.10
     determin
    -0.10
    POSITIVE LOGITS
     Prel
    0.19
     preliminary
    0.19
     evidence
    0.15
     suggest
    0.15
     speculate
    0.15
     experiments
    0.15
    suggest
    0.15
     possibly
    0.15
     suggests
    0.14
     suggestion
    0.14
    Activations Density 1.865%

    No Known Activations