© 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. 88973
    Prev
    Next
    INDEX
    Explanations

    alerts, links, pricing, list, content, data

    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
     imm
    -0.10
    orama
    -0.09
    umble
    -0.08
     domic
    -0.08
    ervo
    -0.08
     swath
    -0.08
     Bare
    -0.08
    99
    -0.08
     Malone
    -0.08
    licken
    -0.08
    POSITIVE LOGITS
     apr
    0.10
     puck
    0.10
     amp
    0.09
    apel
    0.09
    cher
    0.09
     Zig
    0.09
     Crazy
    0.08
     Jordan
    0.08
    stor
    0.08
     institution
    0.08
    Activations Density 0.109%

    No Known Activations