© 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. 88182
    Prev
    Next
    INDEX
    Explanations

    body and somatic connections

    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
     suction
    -0.10
    arat
    -0.09
     compressed
    -0.09
     lé
    -0.09
     cyn
    -0.09
    iani
    -0.09
     gramm
    -0.09
     Cove
    -0.09
     bumped
    -0.09
    ression
    -0.09
    POSITIVE LOGITS
     Body
    0.29
     body
    0.29
     bodily
    0.28
    -body
    0.28
    /body
    0.26
     BODY
    0.26
    Body
    0.26
    body
    0.25
    (body
    0.23
     Bod
    0.22
    Activations Density 0.235%

    No Known Activations