© 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. 49876
    Prev
    Next
    INDEX
    Explanations

    time interval chrono struct

    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
    oci
    -0.08
     homes
    -0.08
     houses
    -0.08
     annoyance
    -0.08
    Cars
    -0.08
     Donate
    -0.07
     friendship
    -0.07
     cars
    -0.07
    med
    -0.07
     friendly
    -0.07
    POSITIVE LOGITS
     penet
    0.11
     chiar
    0.11
     Timeline
    0.10
    "struct
    0.10
    TimeInterval
    0.10
     chromat
    0.10
    imeline
    0.10
     inev
    0.10
     Ritual
    0.10
     chrono
    0.10
    Activations Density 0.864%

    No Known Activations