© 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. 113748
    Prev
    Next
    INDEX
    Explanations

    counting numbers and quantities

    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
     sisters
    -0.10
     brothers
    -0.10
     sons
    -0.10
    cdc
    -0.09
     Sons
    -0.09
     actresses
    -0.09
     husbands
    -0.09
     daughters
    -0.09
    langs
    -0.09
     Sommer
    -0.09
    POSITIVE LOGITS
     achie
    0.10
    ahas
    0.10
    gos
    0.09
    odon
    0.09
    -animation
    0.09
     adults
    0.09
     Marino
    0.09
    mojom
    0.09
    zel
    0.09
     chat
    0.09
    Activations Density 0.040%

    No Known Activations