© 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. 25975
    Prev
    Next
    INDEX
    Explanations

    word followed by they had or Press

    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
    iti
    -0.09
     Gunn
    -0.09
    eler
    -0.08
     Parr
    -0.08
     cr
    -0.08
     present
    -0.08
    anson
    -0.08
     Stop
    -0.07
     Packing
    -0.07
    int
    -0.07
    POSITIVE LOGITS
    lessly
    0.14
     word
    0.12
    -of
    0.12
     ba
    0.12
    .Word
    0.11
     Word
    0.11
    (word
    0.11
    Word
    0.11
    RAP
    0.11
     Wolff
    0.11
    Activations Density 0.020%

    No Known Activations