© 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. 4581
    Prev
    Next
    INDEX
    Explanations

    guy or guys

    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
    nings
    -0.13
    nable
    -0.12
    ARY
    -0.11
    arily
    -0.11
    orian
    -0.11
    arium
    -0.11
    fully
    -0.11
    irst
    -0.11
    ista
    -0.10
    IVE
    -0.10
    POSITIVE LOGITS
    /g
    0.14
    ass
    0.11
    assa
    0.11
     who
    0.10
    assic
    0.10
    dish
    0.10
    enet
    0.09
    amate
    0.09
    hood
    0.09
    ennon
    0.09
    Activations Density 0.019%

    No Known Activations