© 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. 31657
    Prev
    Next
    INDEX
    Explanations

    numbers followed by WHERE, units, commas, or punctuation

    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
     rec
    -0.11
    Å¡t
    -0.10
     rus
    -0.09
     nineteen
    -0.09
    ören
    -0.09
    =bool
    -0.09
    [method
    -0.09
     roma
    -0.09
    <::
    -0.09
     Chapters
    -0.09
    POSITIVE LOGITS
     accordingly
    0.11
     upwards
    0.10
     squirt
    0.10
     etc
    0.09
    nick
    0.09
     bugs
    0.08
     Bugs
    0.08
     Tear
    0.08
    omination
    0.08
     empir
    0.08
    Activations Density 0.360%

    No Known Activations