© 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. 114834
    Prev
    Next
    INDEX
    Explanations

    skip hire sizes

    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
     incons
    -0.09
     demonstr
    -0.09
     paging
    -0.08
    _mC
    -0.08
     Petty
    -0.08
     dimensional
    -0.08
    KC
    -0.08
     indirect
    -0.08
     KC
    -0.08
     Challenger
    -0.08
    POSITIVE LOGITS
    illions
    0.09
    riot
    0.09
     Ca
    0.09
     Nearby
    0.09
     guarante
    0.09
     Tips
    0.09
     Interr
    0.08
     Epid
    0.08
    bee
    0.08
    gear
    0.08
    Activations Density 0.004%

    No Known Activations