© 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. 31088
    Prev
    Next
    INDEX
    Explanations

    other people or things

    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
     inters
    -0.13
    sla
    -0.11
    uur
    -0.10
     Humanity
    -0.10
     intimid
    -0.10
    chner
    -0.10
     BinaryTree
    -0.10
    ses
    -0.10
     Bilder
    -0.10
     pepper
    -0.10
    POSITIVE LOGITS
     strangers
    0.13
     fellow
    0.13
     friends
    0.13
     thousands
    0.13
     ease
    0.12
     Fellow
    0.10
     peers
    0.10
     classmates
    0.10
     pinch
    0.10
     anyone
    0.10
    Activations Density 0.048%

    No Known Activations