© 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. 90045
    Prev
    Next
    INDEX
    Explanations

    and then

    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
    nia
    -0.11
     Mann
    -0.11
     Zwe
    -0.10
    /send
    -0.10
    ubi
    -0.10
    stad
    -0.10
    erra
    -0.10
     Sanders
    -0.10
    /show
    -0.10
    @student
    -0.10
    POSITIVE LOGITS
     receive
    0.14
     await
    0.12
     Await
    0.12
     received
    0.12
     receives
    0.12
     awaited
    0.10
     Receive
    0.10
     they
    0.10
     recieved
    0.10
     obey
    0.10
    Activations Density 0.084%

    No Known Activations