© 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. 5149
    Prev
    Next
    INDEX
    Explanations

    skinny or skeletal description

    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
    sm
    -0.10
     weg
    -0.09
    aca
    -0.09
    sphere
    -0.09
    ros
    -0.09
    ance
    -0.09
    rious
    -0.09
    oha
    -0.09
    sword
    -0.09
     erot
    -0.09
    POSITIVE LOGITS
     dipping
    0.14
     jeans
    0.11
    assed
    0.11
    asses
    0.10
    stery
    0.10
    ners
    0.10
    flix
    0.10
    hoff
    0.09
    ripe
    0.09
    ass
    0.09
    Activations Density 0.006%

    No Known Activations