© 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. 50069
    Prev
    Next
    INDEX
    Explanations

    lists of numbers and editions

    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
     COR
    -0.10
    onde
    -0.10
    /Dk
    -0.09
     McN
    -0.09
     Bol
    -0.09
     Wenn
    -0.09
     Tape
    -0.09
    /goto
    -0.09
    oves
    -0.09
    ager
    -0.09
    POSITIVE LOGITS
    :
    0.13
     vice
    0.12
     possibly
    0.10
     Vice
    0.10
    Anywhere
    0.10
    ibold
    0.09
    —to
    0.09
    oton
    0.09
    oux
    0.09
    ibern
    0.09
    Activations Density 0.532%

    No Known Activations