© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 4175
    Prev
    Next
    INDEX
    Explanations

    numbers and mathematical operations

    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
    9
    -0.10
    orris
    -0.10
    135
    -0.10
    884
    -0.10
     Abrams
    -0.09
     Friedman
    -0.09
     ninth
    -0.09
    139
    -0.09
    997
    -0.09
    ableView
    -0.09
    POSITIVE LOGITS
    50
    0.29
     fifty
    0.28
    48
    0.26
    49
    0.26
    51
    0.26
    52
    0.25
     Fifty
    0.23
    47
    0.22
    500
    0.21
    46
    0.21
    Activations Density 0.453%

    No Known Activations