© 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. 91195
    Prev
    Next
    INDEX
    Explanations

    number of

    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
    bron
    -0.10
    shed
    -0.10
    /o
    -0.10
     deserted
    -0.10
    ình
    -0.10
    ron
    -0.09
    /off
    -0.09
    auté
    -0.09
    actus
    -0.09
    ara
    -0.09
    POSITIVE LOGITS
     crunch
    0.13
     number
    0.13
     numbers
    0.11
     Theory
    0.11
     Crunch
    0.10
     Number
    0.10
     Schl
    0.10
    -number
    0.10
     NUMBER
    0.10
    [".
    0.10
    Activations Density 0.022%

    No Known Activations