© 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. 116032
    Prev
    Next
    INDEX
    Explanations

    as [adjective] as

    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
    krit
    -0.12
    arin
    -0.12
     Raphael
    -0.12
     Vern
    -0.11
     preced
    -0.11
    wort
    -0.11
     constit
    -0.11
     Bir
    -0.11
     booster
    -0.11
     siendo
    -0.11
    POSITIVE LOGITS
     as
    0.17
     imaginable
    0.08
     quanto
    0.08
     Trap
    0.08
    ipe
    0.07
    aku
    0.07
    omo
    0.07
     trap
    0.07
     Kenny
    0.07
    asser
    0.07
    Activations Density 0.042%

    No Known Activations