© 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. 31556
    Prev
    Next
    INDEX
    Explanations

    file extension

    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
    -basket
    -0.08
     Around
    -0.08
     mitochond
    -0.08
    ovi
    -0.07
     Hex
    -0.07
     Sq
    -0.07
    .jupiter
    -0.07
     mut
    -0.07
     physic
    -0.07
     sábado
    -0.07
    POSITIVE LOGITS
    .serialize
    0.11
     Developer
    0.11
    cio
    0.10
    imos
    0.10
     forg
    0.10
     Gam
    0.10
     tongue
    0.10
    DK
    0.10
    (Build
    0.10
    dni
    0.10
    Activations Density 0.023%

    No Known Activations