© 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. 16744
    Prev
    Next
    INDEX
    Explanations

    code comments and conditions

    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
     liked
    -0.08
    icz
    -0.07
    cai
    -0.07
     clad
    -0.07
     Prayer
    -0.07
     welcome
    -0.06
     Conserv
    -0.06
     conserv
    -0.06
    rij
    -0.06
     bib
    -0.06
    POSITIVE LOGITS
    tl
    0.11
    ivor
    0.11
     appar
    0.10
    asley
    0.10
    oro
    0.10
    abis
    0.10
    itude
    0.10
    unga
    0.10
    tos
    0.10
    ever
    0.10
    Activations Density 0.001%

    No Known Activations