© 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. 91135
    Prev
    Next
    INDEX
    Explanations

    talking with people

    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
     gras
    -0.12
     Discussions
    -0.12
     endless
    -0.12
    oth
    -0.11
     silent
    -0.11
     Agenda
    -0.11
    aeda
    -0.11
     maj
    -0.11
     comprehension
    -0.11
     kissed
    -0.11
    POSITIVE LOGITS
     friendly
    0.11
     neighbor
    0.11
     neighbour
    0.11
     lanc
    0.09
    Neighbor
    0.08
     confidence
    0.08
     strangers
    0.08
    Friendly
    0.08
     Friendly
    0.08
    Neighbors
    0.08
    Activations Density 0.021%

    No Known Activations