© 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
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 28836
    Prev
    Next
    INDEX
    Explanations

    over the

    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
     recognise
    -0.12
     util
    -0.12
     recognised
    -0.12
    bdb
    -0.12
     organis
    -0.12
     organisers
    -0.11
     STREAM
    -0.11
     recogn
    -0.11
    ugin
    -0.11
     utilise
    -0.11
    POSITIVE LOGITS
    iasm
    0.07
    \\"
    0.07
    weg
    0.07
    riz
    0.07
     parad
    0.07
     Nacht
    0.07
     Uni
    0.07
    Refs
    0.07
     pendant
    0.06
     palm
    0.06
    Activations Density 0.026%

    No Known Activations