© 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. 113244
    Prev
    Next
    INDEX
    Explanations

    points in time

    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
     daily
    -0.14
     tomorrow
    -0.10
     morning
    -0.10
    Daily
    -0.10
     nightly
    -0.10
     evenings
    -0.10
     weekday
    -0.09
     Overnight
    -0.09
    /day
    -0.09
    ilst
    -0.09
    POSITIVE LOGITS
     midway
    0.30
     halfway
    0.26
     nearing
    0.20
     throughout
    0.19
     midpoint
    0.17
     Throughout
    0.17
     early
    0.17
    Towards
    0.16
     mid
    0.16
     middle
    0.16
    Activations Density 0.358%

    No Known Activations