© 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. 49783
    Prev
    Next
    INDEX
    Explanations

    body parts or biological structures

    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
     Necklace
    -0.12
     dele
    -0.12
     wrists
    -0.11
     Shirt
    -0.11
    (Index
    -0.11
    enberg
    -0.10
    571
    -0.10
     jaws
    -0.10
    /Base
    -0.10
    ibe
    -0.10
    POSITIVE LOGITS
    _assert
    0.08
    ilik
    0.07
     Zy
    0.07
    abet
    0.07
     pe
    0.07
     sideline
    0.07
    apon
    0.07
    splash
    0.07
     summers
    0.07
     us
    0.07
    Activations Density 0.008%

    No Known Activations