© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 3586
    Prev
    Next
    INDEX
    Explanations

    get going / get mad / get into / get worse / get married / get across / get up / get straight

    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
    Negative Logits
    lessly
    -0.11
     surrounded
    -0.11
    /un
    -0.11
    ulis
    -0.10
     Lud
    -0.10
    fen
    -0.10
    quil
    -0.10
     Butt
    -0.10
     Lobby
    -0.10
    sten
    -0.10
    POSITIVE LOGITS
     supper
    0.10
    ingles
    0.10
     Spawn
    0.09
    ike
    0.08
    edad
    0.08
    aney
    0.08
     receipt
    0.08
     spawn
    0.08
     dus
    0.08
    uppe
    0.08
    Activations Density 0.014%

    No Known Activations