© 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. 17396
    Prev
    Next
    INDEX
    Explanations

    chance to X

    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
     Cliff
    -0.10
     virgin
    -0.10
    636
    -0.10
    akh
    -0.10
     seeming
    -0.10
     Stevenson
    -0.09
    pcs
    -0.09
    altar
    -0.09
     Harr
    -0.09
    Td
    -0.09
    POSITIVE LOGITS
     opportunity
    0.29
     chance
    0.27
     Opportunity
    0.22
     Chance
    0.20
    Chance
    0.18
     opportunities
    0.18
     time
    0.16
     ÑĥÑģп
    0.15
     Opportunities
    0.15
     chances
    0.15
    Activations Density 0.038%

    No Known Activations