© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 15770
    Prev
    Next
    INDEX
    Explanations

    body parts and middle points

    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
    jem
    -0.11
    achel
    -0.11
    cape
    -0.10
     aging
    -0.10
     Verd
    -0.10
     lett
    -0.10
     Hopkins
    -0.10
     temporarily
    -0.09
    .bel
    -0.09
     dof
    -0.09
    POSITIVE LOGITS
     halfway
    0.16
     midpoint
    0.14
     knees
    0.12
     elbows
    0.12
     midway
    0.12
     tops
    0.11
     mid
    0.11
     midfield
    0.10
     LINE
    0.09
     previews
    0.09
    Activations Density 0.076%

    No Known Activations