© 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. 30988
    Prev
    Next
    INDEX
    Explanations

    Noah, NOAA, nozzle

    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
    eness
    -0.12
    iento
    -0.10
    els
    -0.10
    estro
    -0.10
    eh
    -0.09
     Markt
    -0.09
    ech
    -0.09
    .mybatisplus
    -0.09
     spoilers
    -0.09
    mentation
    -0.09
    POSITIVE LOGITS
    ozy
    0.11
     Ark
    0.11
     ark
    0.10
    /cop
    0.09
    Ark
    0.09
     discern
    0.09
    ös
    0.09
    ly
    0.08
    icorn
    0.08
    ugin
    0.08
    Activations Density 0.008%

    No Known Activations