© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48371
    Prev
    Next
    INDEX
    Explanations

    teenager

    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
     kindergarten
    -0.22
     preschool
    -0.21
     children
    -0.18
     childhood
    -0.17
     child
    -0.16
     CHILD
    -0.16
     Elementary
    -0.15
     childish
    -0.15
    children
    -0.15
     elementary
    -0.15
    POSITIVE LOGITS
     Teen
    0.24
     teenager
    0.23
     teens
    0.22
     Teens
    0.22
     teen
    0.22
     teenagers
    0.22
    Teen
    0.21
     teenage
    0.20
    teen
    0.16
     adolescents
    0.16
    Activations Density 0.143%

    No Known Activations