© 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. 18216
    Prev
    Next
    INDEX
    Explanations

    running, walking, and jogging

    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
     backstage
    -0.09
     wizard
    -0.08
     teamwork
    -0.08
     terminal
    -0.08
     nonsense
    -0.08
    junction
    -0.08
    unction
    -0.08
     cabinet
    -0.08
     gere
    -0.08
    bum
    -0.07
    POSITIVE LOGITS
     jog
    0.25
     jogging
    0.24
     cycling
    0.21
     Jog
    0.20
     runners
    0.20
     exercising
    0.19
     biking
    0.19
     runner
    0.18
     exercise
    0.18
     exercised
    0.18
    Activations Density 0.233%

    No Known Activations