© 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. 27946
    Prev
    Next
    INDEX
    Explanations

    come

    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
    -0.10
    span
    -0.08
    ize
    -0.08
    uish
    -0.08
     Span
    -0.08
    semble
    -0.08
    tern
    -0.08
    re
    -0.07
    imize
    -0.07
     verge
    -0.07
    POSITIVE LOGITS
    upp
    0.17
     come
    0.14
     Come
    0.12
    Come
    0.12
    come
    0.12
    backs
    0.12
    .liferay
    0.12
    ati
    0.11
     Pend
    0.11
     comeback
    0.11
    Activations Density 0.016%

    No Known Activations