© 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. 50697
    Prev
    Next
    INDEX
    Explanations

    body parts and associated 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
    -like
    -0.09
     Bout
    -0.08
    -esque
    -0.07
     mid
    -0.07
     hips
    -0.07
    lia
    -0.07
    -shaped
    -0.07
     conven
    -0.06
    -form
    -0.06
    -proof
    -0.06
    POSITIVE LOGITS
     tapping
    0.14
    /arm
    0.13
    /head
    0.13
    -,
    0.13
    -to
    0.12
    -based
    0.12
     toss
    0.12
    Äįe
    0.12
    -Based
    0.12
     waving
    0.12
    Activations Density 0.067%

    No Known Activations