© 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. 89740
    Prev
    Next
    INDEX
    Explanations

    country names, events, or activities

    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
     Autof
    -0.08
     during
    -0.08
     meanwhile
    -0.08
    yas
    -0.07
    alion
    -0.07
    iates
    -0.07
     simult
    -0.07
     mush
    -0.07
    bir
    -0.07
     simultaneously
    -0.07
    POSITIVE LOGITS
    iga
    0.13
     Pom
    0.12
    cke
    0.12
     onward
    0.12
    erer
    0.12
     onwards
    0.12
     Zum
    0.11
     period
    0.11
     yesterday
    0.11
     Reload
    0.11
    Activations Density 0.232%

    No Known Activations