© 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. 16506
    Prev
    Next
    INDEX
    Explanations

    network of connections

    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
     authorised
    -0.11
     authorized
    -0.10
    authorized
    -0.10
    angan
    -0.10
     /*----------------------------------------------------------------
    -0.10
     delights
    -0.10
    .dw
    -0.09
     recurs
    -0.09
    enheim
    -0.09
    anonymous
    -0.09
    POSITIVE LOGITS
     networks
    0.33
     network
    0.28
     connections
    0.27
    -network
    0.24
    /network
    0.23
     Networks
    0.23
    network
    0.22
     contacts
    0.21
     networking
    0.19
    connections
    0.19
    Activations Density 0.231%

    No Known Activations