© 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. 4181
    Prev
    Next
    INDEX
    Explanations

    citations or special identifiers

    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
    imet
    -0.11
    arak
    -0.11
     ÂŃ
    -0.10
     ration
    -0.10
    berman
    -0.09
     earm
    -0.09
    vos
    -0.09
     gag
    -0.09
     Lak
    -0.09
     undes
    -0.09
    POSITIVE LOGITS
     quot
    0.14
    sitemap
    0.09
    iten
    0.09
    )}↵↵
    0.08
    nel
    0.08
    orr
    0.08
     climbing
    0.08
     Journal
    0.08
    orney
    0.08
     timeline
    0.08
    Activations Density 0.026%

    No Known Activations