© 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. 91447
    Prev
    Next
    INDEX
    Explanations

    date expressions and time units

    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
     hilar
    -0.10
     reverted
    -0.08
     antibiot
    -0.08
    spl
    -0.08
    alic
    -0.08
     fringe
    -0.08
    lore
    -0.08
     litter
    -0.08
     ÑĤек
    -0.08
    ernals
    -0.08
    POSITIVE LOGITS
     Cooler
    0.10
    essian
    0.09
    mars
    0.09
    ius
    0.09
    .sax
    0.09
    -ad
    0.09
    HZ
    0.09
     cigar
    0.09
     Pols
    0.09
    ella
    0.09
    Activations Density 0.001%

    No Known Activations