© 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. 17473
    Prev
    Next
    INDEX
    Explanations

    quantity or degree comparison

    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
    oldt
    -0.13
    stead
    -0.10
    lies
    -0.09
     loft
    -0.09
    ota
    -0.09
     cape
    -0.09
    ries
    -0.09
    /API
    -0.09
    otal
    -0.09
     hors
    -0.09
    POSITIVE LOGITS
     enough
    0.19
     exceeding
    0.18
     almost
    0.17
     comparable
    0.17
     beyond
    0.16
     surpass
    0.16
     far
    0.15
     verg
    0.15
     Enough
    0.14
    almost
    0.14
    Activations Density 0.355%

    No Known Activations