© 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. 49339
    Prev
    Next
    INDEX
    Explanations

    to seconds/that/the/be/point/some/your/android/a

    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
    inq
    -0.09
     Bes
    -0.09
    do
    -0.09
    ensa
    -0.09
    elp
    -0.09
     Carlton
    -0.08
    Bes
    -0.08
    tiny
    -0.08
     try
    -0.08
    anzi
    -0.08
    POSITIVE LOGITS
     midst
    0.12
     downwards
    0.11
     perfection
    0.11
     fullest
    0.11
     Chop
    0.10
     directions
    0.10
     direction
    0.10
     nächsten
    0.10
     Exhibit
    0.09
     Huffman
    0.09
    Activations Density 0.211%

    No Known Activations