© 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. 30983
    Prev
    Next
    INDEX
    Explanations

    matthew or matt followed by a name

    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
    ered
    -0.10
    houses
    -0.09
    hart
    -0.08
    eries
    -0.08
    idot
    -0.08
    ight
    -0.08
    lest
    -0.08
     separ
    -0.08
     coco
    -0.08
    ajes
    -0.07
    POSITIVE LOGITS
    ting
    0.15
    thew
    0.12
    achine
    0.12
    uration
    0.12
    imore
    0.12
    .pyplot
    0.11
    illard
    0.11
    ilda
    0.11
    anus
    0.11
    apult
    0.11
    Activations Density 0.032%

    No Known Activations