© 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. 112278
    Prev
    Next
    INDEX
    Explanations

    names like brenner, rene, irene, wen

    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
    ony
    -0.12
    iap
    -0.12
    olas
    -0.11
     Randall
    -0.11
     concession
    -0.10
     kickoff
    -0.10
    pitch
    -0.10
     mang
    -0.10
     qualifier
    -0.09
    inion
    -0.09
    POSITIVE LOGITS
    ascar
    0.08
    nes
    0.08
    dot
    0.08
    /left
    0.08
     Lair
    0.08
    fname
    0.07
    hausen
    0.07
    cker
    0.07
    nie
    0.07
     grouped
    0.07
    Activations Density 0.012%

    No Known Activations