© 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. 31118
    Prev
    Next
    INDEX
    Explanations

    continental, control, contract, contingency

    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
    unde
    -0.09
    ifice
    -0.09
    unas
    -0.08
    hani
    -0.08
     unknow
    -0.08
    icer
    -0.08
    stage
    -0.08
    amate
    -0.07
     ung
    -0.07
     resent
    -0.07
    POSITIVE LOGITS
     Cont
    0.18
     kont
    0.18
     contingency
    0.17
     contours
    0.17
    .Cont
    0.17
    -cont
    0.17
    (cont
    0.15
     cont
    0.15
    inue
    0.15
     conting
    0.15
    Activations Density 0.100%

    No Known Activations