© 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. 113754
    Prev
    Next
    INDEX
    Explanations

    Miles, meter, milestones

    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
    hir
    -0.10
    etty
    -0.09
    oles
    -0.09
     chilling
    -0.09
    lights
    -0.08
    osa
    -0.08
    ulary
    -0.08
    gaard
    -0.08
    Liked
    -0.08
    ivity
    -0.08
    POSITIVE LOGITS
    dden
    0.10
    plit
    0.10
     Yam
    0.09
     Markus
    0.09
     Pom
    0.09
    kc
    0.09
     milestones
    0.09
    king
    0.09
     conscious
    0.09
    izen
    0.09
    Activations Density 0.073%

    No Known Activations