© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 92270
    Prev
    Next
    INDEX
    Explanations

    children's activities and gifts

    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
     youngsters
    -0.12
     teen
    -0.11
    omid
    -0.11
     teens
    -0.11
     girls
    -0.11
     teenagers
    -0.11
     young
    -0.10
    lag
    -0.10
     flats
    -0.10
     recl
    -0.10
    POSITIVE LOGITS
     playground
    0.16
     cray
    0.16
     toy
    0.15
     toys
    0.14
     Santa
    0.14
     homework
    0.14
     elementary
    0.13
     Halloween
    0.13
     play
    0.13
     santa
    0.13
    Activations Density 0.129%

    No Known Activations