© 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. 16528
    Prev
    Next
    INDEX
    Explanations

    wish i could

    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
    try
    -0.11
    enty
    -0.11
     attempt
    -0.10
     try
    -0.10
     graveyard
    -0.10
    /trunk
    -0.10
    TRY
    -0.09
     milan
    -0.09
     euler
    -0.09
    TI
    -0.09
    POSITIVE LOGITS
     somehow
    0.17
     magically
    0.17
     magic
    0.11
     mirac
    0.11
     clone
    0.11
     teleport
    0.10
     rewind
    0.10
     undo
    0.09
     know
    0.09
    orda
    0.09
    Activations Density 0.027%

    No Known Activations