© 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. 33718
    Prev
    Next
    INDEX
    Explanations

    tal names

    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
    sert
    -0.10
     Sanford
    -0.08
     passing
    -0.08
    olo
    -0.08
    lying
    -0.07
    atorium
    -0.07
    anos
    -0.07
     cold
    -0.07
    erras
    -0.07
     Entrepreneur
    -0.07
    POSITIVE LOGITS
     tal
    0.15
     Tal
    0.13
    isman
    0.13
    bot
    0.12
    ocr
    0.12
     Tale
    0.11
    ented
    0.11
    boys
    0.11
    oned
    0.11
    ourd
    0.11
    Activations Density 0.044%

    No Known Activations