© 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. 48874
    Prev
    Next
    INDEX
    Explanations

    producer names and models

    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
     strange
    -0.09
     nuts
    -0.08
    oom
    -0.08
    Strange
    -0.08
     Balk
    -0.08
     Leafs
    -0.08
     GFX
    -0.08
     cakes
    -0.08
     nood
    -0.08
     jam
    -0.08
    POSITIVE LOGITS
     medium
    0.13
     Sony
    0.12
     Samsung
    0.12
     Nike
    0.11
    agate
    0.11
     Canon
    0.11
     Panasonic
    0.11
     Motorola
    0.11
    medium
    0.11
    0.11
    Activations Density 1.349%

    No Known Activations