© 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. 33014
    Prev
    Next
    INDEX
    Explanations

    .com showcases

    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
    iste
    -0.08
     Cancel
    -0.07
     Patreon
    -0.07
    odie
    -0.07
     Braun
    -0.07
     âĿ¤
    -0.07
     incred
    -0.07
     Patron
    -0.07
    ices
    -0.07
     Mig
    -0.07
    POSITIVE LOGITS
     preceded
    0.11
     Niet
    0.10
     cage
    0.10
     Cage
    0.10
     thrust
    0.10
     Furn
    0.10
    418
    0.10
     Fried
    0.10
    \"
    0.10
     Ajax
    0.10
    Activations Density 0.012%

    No Known Activations