© 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. 4614
    Prev
    Next
    INDEX
    Explanations

    numbers and file names

    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
     McMaster
    -0.11
    lear
    -0.10
    aler
    -0.10
    isseur
    -0.09
     Rubio
    -0.09
     Surv
    -0.09
     pinch
    -0.09
    еÑģÑĤв
    -0.09
    illon
    -0.09
    vik
    -0.09
    POSITIVE LOGITS
    ieties
    0.09
     sage
    0.09
     groot
    0.09
    kal
    0.09
     Installer
    0.09
    asso
    0.09
     serious
    0.09
    /bus
    0.09
     upt
    0.08
     itch
    0.08
    Activations Density 0.003%

    No Known Activations