© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 115219
    Prev
    Next
    INDEX
    Explanations

    uptown, upturn, upsets, upstart

    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
    porter
    -0.08
    adata
    -0.08
    belt
    -0.08
    lint
    -0.07
     frag
    -0.07
    pedia
    -0.07
    ossil
    -0.07
    labs
    -0.07
    itionally
    -0.07
     Bookmark
    -0.07
    POSITIVE LOGITS
     uplift
    0.16
     ups
    0.15
     upt
    0.15
     upright
    0.15
     uplifting
    0.14
     uprising
    0.14
     overs
    0.12
    UPI
    0.12
    >((
    0.12
    spir
    0.12
    Activations Density 0.011%

    No Known Activations