© 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. 47506
    Prev
    Next
    INDEX
    Explanations

    sensitive data/information

    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
    abee
    -0.10
    isted
    -0.10
    acket
    -0.10
    /by
    -0.09
    ing
    -0.09
     fashion
    -0.09
    edin
    -0.09
    ings
    -0.09
    jos
    -0.09
     conceived
    -0.09
    POSITIVE LOGITS
    /select
    0.12
     spots
    0.12
     areas
    0.11
    -sensitive
    0.11
     enough
    0.11
     vulnerable
    0.10
     underside
    0.10
     inner
    0.10
     sensitive
    0.10
     area
    0.10
    Activations Density 0.014%

    No Known Activations