© 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. 18135
    Prev
    Next
    INDEX
    Explanations

    using, with, by, via

    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
     Closet
    -0.11
     closet
    -0.11
     Mist
    -0.09
    toa
    -0.09
     curt
    -0.08
     Benson
    -0.08
    ambi
    -0.08
     oral
    -0.08
     Ernst
    -0.08
     amb
    -0.07
    POSITIVE LOGITS
     pry
    0.17
     force
    0.14
     pushes
    0.14
    force
    0.14
     pushing
    0.14
     forcibly
    0.13
     nud
    0.13
     splitter
    0.12
     FORCE
    0.12
    kos
    0.12
    Activations Density 0.027%

    No Known Activations