© 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. 16376
    Prev
    Next
    INDEX
    Explanations

    newly updated or introduced things

    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
     sendData
    -0.08
    ()(
    -0.08
     expectedResult
    -0.08
     diz
    -0.07
    ifu
    -0.07
     processData
    -0.07
    bie
    -0.07
     poil
    -0.07
     masa
    -0.07
    myp
    -0.07
    POSITIVE LOGITS
     new
    1.00
    new
    0.76
    æĸ°
    0.70
    (new
    0.68
    	new
    0.63
    -new
    0.63
     newly
    0.62
     newfound
    0.60
     нов
    0.60
    =new
    0.58
    Activations Density 2.843%

    No Known Activations