© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 116758
    Prev
    Next
    INDEX
    Explanations

    maters, Matlab, Matplotlib, maturation

    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
    plex
    -0.09
    onta
    -0.09
    oops
    -0.08
     lanz
    -0.08
    eing
    -0.08
     Cross
    -0.08
    umo
    -0.08
    een
    -0.07
    gal
    -0.07
    mand
    -0.07
    POSITIVE LOGITS
    iben
    0.13
    atu
    0.13
    imore
    0.12
    buat
    0.11
     maturity
    0.11
    arta
    0.11
    Enlarge
    0.10
    manship
    0.10
    macro
    0.10
     Macro
    0.10
    Activations Density 0.012%

    No Known Activations