© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 116147
    Prev
    Next
    INDEX
    Explanations

    sentence structure connectors

    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
     Tod
    -0.12
     continually
    -0.10
    )..
    -0.10
     WOW
    -0.10
     Whats
    -0.10
    Whats
    -0.10
     Lets
    -0.10
     Pirate
    -0.10
     OMG
    -0.10
    /ag
    -0.09
    POSITIVE LOGITS
    And
    0.17
     And
    0.16
    Except
    0.10
    .And
    0.10
    Or
    0.10
    _and
    0.10
    â̦and
    0.10
    —and
    0.10
     Or
    0.10
    Which
    0.09
    Activations Density 0.029%

    No Known Activations