© 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. 89521
    Prev
    Next
    INDEX
    Explanations

    issues and attachments

    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
     oft
    -0.11
     Eval
    -0.11
    946
    -0.11
    ube
    -0.11
     Abb
    -0.10
     sometimes
    -0.10
    uben
    -0.10
     Natur
    -0.10
    uid
    -0.10
    dorf
    -0.10
    POSITIVE LOGITS
     lurking
    0.12
     present
    0.12
     possible
    0.11
     arising
    0.11
     remaining
    0.11
     potential
    0.11
    /all
    0.10
     necessary
    0.10
     vorhand
    0.10
     encountered
    0.10
    Activations Density 0.181%

    No Known Activations