© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 50624
    Prev
    Next
    INDEX
    Explanations

    body parts, feet, or related actions

    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
     gor
    -0.09
    ODB
    -0.09
    naire
    -0.08
     bends
    -0.08
    omal
    -0.08
    esses
    -0.08
    reds
    -0.08
    cas
    -0.08
    oses
    -0.08
    aries
    -0.08
    POSITIVE LOGITS
     feet
    0.11
     Feet
    0.11
     noises
    0.10
     Emanuel
    0.10
    -long
    0.10
    (fe
    0.10
     fungus
    0.10
    esk
    0.10
    emp
    0.10
    -focused
    0.10
    Activations Density 0.010%

    No Known Activations