© 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. 88431
    Prev
    Next
    INDEX
    Explanations

    how things work or operate

    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
    ents
    -0.09
     liber
    -0.09
     jihad
    -0.08
     Daly
    -0.08
     med
    -0.08
     eg
    -0.07
     chim
    -0.07
    emes
    -0.07
    td
    -0.07
    Tower
    -0.07
    POSITIVE LOGITS
     operates
    0.15
     operate
    0.13
     workings
    0.13
     functioning
    0.13
     Works
    0.12
    operate
    0.11
     operating
    0.11
    bast
    0.11
     Oper
    0.11
    inee
    0.11
    Activations Density 0.004%

    No Known Activations