© 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. 49696
    Prev
    Next
    INDEX
    Explanations

    donor-derived or paternal leakage

    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
     Pain
    -0.10
    itat
    -0.10
     Mund
    -0.09
    sing
    -0.09
    cec
    -0.09
     aug
    -0.09
    GRAPH
    -0.09
    quine
    -0.09
     Childhood
    -0.09
     tas
    -0.09
    POSITIVE LOGITS
     traces
    0.18
     lingering
    0.17
     residual
    0.17
     leftover
    0.16
     leftovers
    0.16
     remnants
    0.15
     semen
    0.15
     linger
    0.15
     residue
    0.15
     seminal
    0.13
    Activations Density 0.036%

    No Known Activations