© 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. 16886
    Prev
    Next
    INDEX
    Explanations

    roll up or roll out

    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
     Gos
    -0.10
     Andersen
    -0.10
     electr
    -0.09
     wrench
    -0.09
     Stap
    -0.09
    matrix
    -0.09
    jes
    -0.09
    ichen
    -0.09
     stap
    -0.09
     aud
    -0.09
    POSITIVE LOGITS
     sleeves
    0.13
     up
    0.12
     trousers
    0.11
     cuffs
    0.10
     rolled
    0.09
    allel
    0.09
     cigaret
    0.09
     cigarettes
    0.09
     hacia
    0.09
     Rolled
    0.09
    Activations Density 0.005%

    No Known Activations