© 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. 28291
    Prev
    Next
    INDEX
    Explanations

    inserting data

    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
     stom
    -0.11
     convo
    -0.11
     Kab
    -0.10
     conversations
    -0.10
     Conversation
    -0.10
    ncy
    -0.10
    Conversation
    -0.10
     Fancy
    -0.10
    ALAR
    -0.09
     temporarily
    -0.09
    POSITIVE LOGITS
     parted
    0.09
     broken
    0.09
     invol
    0.09
     Gov
    0.09
    Unexpected
    0.08
     canal
    0.08
    uso
    0.08
    Broken
    0.08
     Diamonds
    0.08
     outright
    0.08
    Activations Density 0.013%

    No Known Activations