© 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. 89324
    Prev
    Next
    INDEX
    Explanations

    mean age

    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
     aggression
    -0.09
    ter
    -0.09
    erry
    -0.08
     statistics
    -0.08
     begr
    -0.08
     upto
    -0.08
     comparative
    -0.08
     atroc
    -0.08
     benchmark
    -0.08
     attent
    -0.08
    POSITIVE LOGITS
     mean
    0.14
     age
    0.13
    mean
    0.12
    iali
    0.12
     overwhelmingly
    0.12
     years
    0.12
     ages
    0.11
     Age
    0.11
    _mean
    0.11
     SD
    0.11
    Activations Density 2.804%

    No Known Activations