© 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. 17662
    Prev
    Next
    INDEX
    Explanations

    catching up

    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
    emann
    -0.10
     Catalyst
    -0.09
    enter
    -0.09
     enters
    -0.09
     low
    -0.09
     flex
    -0.09
    -focus
    -0.09
     enter
    -0.09
    izen
    -0.09
     entering
    -0.08
    POSITIVE LOGITS
     overt
    0.32
     catch
    0.29
     catching
    0.28
     intercept
    0.27
     catches
    0.27
     caught
    0.25
    catch
    0.25
     intercepted
    0.25
     Catch
    0.25
    Catch
    0.22
    Activations Density 0.127%

    No Known Activations