© 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. 7872
    Prev
    Next
    INDEX
    Explanations

    legal or policy language

    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
    zem
    -0.09
     Stanton
    -0.09
    PIN
    -0.08
     med
    -0.08
    XT
    -0.08
     Vall
    -0.08
     Osborne
    -0.08
     Calder
    -0.08
     torn
    -0.08
    agle
    -0.08
    POSITIVE LOGITS
    sy
    0.10
    Trim
    0.10
     Moo
    0.10
    ocks
    0.10
    rog
    0.09
    rvine
    0.09
     â
    0.09
     crunch
    0.09
    icy
    0.09
     Wal
    0.09
    Activations Density 0.232%

    No Known Activations