© 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. 15575
    Prev
    Next
    INDEX
    Explanations

    through or thru

    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
    s
    -0.16
    inge
    -0.11
    ses
    -0.10
    ered
    -0.10
     pis
    -0.10
    alytics
    -0.10
    ping
    -0.10
    alty
    -0.09
    sid
    -0.09
    erge
    -0.09
    POSITIVE LOGITS
    ogh
    0.18
    ough
    0.13
    out
    0.12
    gether
    0.12
    amp
    0.11
    igh
    0.10
    armor
    0.09
    formation
    0.09
    ÃŁer
    0.09
    ร
    0.09
    Activations Density 0.004%

    No Known Activations