© 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. 3765
    Prev
    Next
    INDEX
    Explanations

    one-to-one relationships

    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
    ita
    -0.10
     Moss
    -0.10
    !=(
    -0.09
    adera
    -0.09
    holm
    -0.08
    opensource
    -0.08
     imper
    -0.08
    alach
    -0.08
    trace
    -0.08
     Imper
    -0.08
    POSITIVE LOGITS
    -one
    0.13
    (one
    0.11
    ividual
    0.10
     ance
    0.10
     ONE
    0.10
     singled
    0.10
     individually
    0.10
    oley
    0.10
    ToOne
    0.10
     individ
    0.10
    Activations Density 0.019%

    No Known Activations