© 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. 48984
    Prev
    Next
    INDEX
    Explanations

    at

    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
    ward
    -0.12
    vol
    -0.12
    er
    -0.10
    ingly
    -0.10
    holding
    -0.10
    wards
    -0.09
    hart
    -0.09
    cem
    -0.09
    hold
    -0.09
     ordin
    -0.09
    POSITIVE LOGITS
    s
    0.17
    ypical
    0.13
     least
    0.11
    rophic
    0.11
    ted
    0.11
    rophy
    0.10
    lassian
    0.10
    samp
    0.10
    nip
    0.10
    kinson
    0.10
    Activations Density 0.001%

    No Known Activations