© 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. 89478
    Prev
    Next
    INDEX
    Explanations

    holiday and hormones, often followed by location or type (home, Inn)

    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
    atur
    -0.12
    Altern
    -0.10
    rale
    -0.09
    mind
    -0.09
    lander
    -0.09
     Watkins
    -0.09
    JOR
    -0.09
    pell
    -0.09
    iling
    -0.09
    erp
    -0.09
    POSITIVE LOGITS
    osate
    0.11
    quin
    0.10
    ede
    0.10
    (s
    0.09
    echa
    0.09
    ález
    0.09
    /path
    0.09
     Forge
    0.09
    huge
    0.09
     apt
    0.08
    Activations Density 0.068%

    No Known Activations