© 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. 18104
    Prev
    Next
    INDEX
    Explanations

    golf and conference

    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
     families
    -0.12
     homework
    -0.11
    School
    -0.11
     Families
    -0.10
     Childhood
    -0.10
    iten
    -0.10
     childhood
    -0.10
     Homework
    -0.10
     apprent
    -0.10
    ISODE
    -0.10
    POSITIVE LOGITS
     golf
    0.14
     remar
    0.13
     conference
    0.11
     Golf
    0.11
     Conference
    0.10
     gourmet
    0.09
     rem
    0.09
     gol
    0.09
     mover
    0.09
     confiscated
    0.08
    Activations Density 0.030%

    No Known Activations