© 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. 90814
    Prev
    Next
    INDEX
    Explanations

    adult preceded by words like child

    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
    ibal
    -0.10
    boy
    -0.10
     globalization
    -0.10
    ï¸ı
    -0.10
     cus
    -0.10
    注
    -0.10
     Freel
    -0.09
     subs
    -0.09
     supers
    -0.09
    incl
    -0.09
    POSITIVE LOGITS
    ress
    0.13
    -child
    0.13
    /ad
    0.13
    thood
    0.12
    icide
    0.12
    -aged
    0.12
    -sized
    0.11
     Swim
    0.11
     Sized
    0.11
    umer
    0.11
    Activations Density 0.075%

    No Known Activations