© 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. 49502
    Prev
    Next
    INDEX
    Explanations

    time elapsed leading to eventual outcome

    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
     temporarily
    -0.09
     permanently
    -0.08
     crossing
    -0.07
    ushi
    -0.07
    TRS
    -0.07
     facet
    -0.07
     hm
    -0.07
    -Bar
    -0.07
     post
    -0.07
     micro
    -0.07
    POSITIVE LOGITS
     Eventually
    0.14
     arrived
    0.14
     Soon
    0.14
    finally
    0.14
     eventually
    0.13
     finally
    0.13
     arrives
    0.13
    Eventually
    0.13
     later
    0.13
     Finally
    0.12
    Activations Density 0.014%

    No Known Activations