© 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. 89082
    Prev
    Next
    INDEX
    Explanations

    jogging and runners

    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
     lashes
    -0.09
    ing
    -0.08
    stoff
    -0.08
    uder
    -0.08
     organ
    -0.08
     ideal
    -0.07
    imit
    -0.07
    _DIRS
    -0.07
     spec
    -0.07
    fu
    -0.07
    POSITIVE LOGITS
    gers
    0.17
     jog
    0.16
    ging
    0.14
     jogging
    0.13
     Jog
    0.12
    walker
    0.12
    /run
    0.12
     lightly
    0.11
    ger
    0.11
    refresh
    0.11
    Activations Density 0.002%

    No Known Activations