© 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. 90727
    Prev
    Next
    INDEX
    Explanations

    bone and muscle anatomy

    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
    Contain
    -0.11
    swire
    -0.11
     containment
    -0.11
    ERP
    -0.11
    soc
    -0.11
    warf
    -0.11
    DES
    -0.11
     Canterbury
    -0.11
    .Dot
    -0.10
     poil
    -0.10
    POSITIVE LOGITS
     muscle
    0.09
     anatom
    0.09
     cic
    0.08
     unh
    0.08
     junction
    0.08
     area
    0.07
     bone
    0.07
     muscles
    0.07
     bones
    0.07
     region
    0.07
    Activations Density 0.029%

    No Known Activations