© 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. 4451
    Prev
    Next
    INDEX
    Explanations

    people descriptors

    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
     ages
    -0.11
     elders
    -0.11
     aged
    -0.11
     Aging
    -0.11
     ageing
    -0.11
     aging
    -0.10
    /manual
    -0.10
     granny
    -0.10
    OldData
    -0.10
     grandfather
    -0.10
    POSITIVE LOGITS
     (>
    0.13
     McA
    0.09
    /new
    0.08
     syndrome
    0.08
    lix
    0.08
    arkin
    0.08
     casa
    0.08
     Gand
    0.08
    ynamo
    0.07
     deflate
    0.07
    Activations Density 0.003%

    No Known Activations