© 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. 48791
    Prev
    Next
    INDEX
    Explanations

    service, network, treatments, purpose

    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
     incom
    -0.08
    rv
    -0.08
     Bradley
    -0.08
    iner
    -0.07
     and
    -0.07
    ronic
    -0.07
     Nec
    -0.07
    oa
    -0.07
    -ne
    -0.06
     uncomp
    -0.06
    POSITIVE LOGITS
    /lab
    0.12
     fundament
    0.11
     Lab
    0.11
    ,eg
    0.11
    perf
    0.11
     mann
    0.11
     ipairs
    0.10
     replicated
    0.10
    lab
    0.10
     Cat
    0.10
    Activations Density 0.038%

    No Known Activations