© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 25019
    Prev
    Next
    INDEX
    Explanations

    float and floating terms

    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
    Negative Logits
     footprint
    -0.10
     Reactive
    -0.10
    aron
    -0.09
    OTA
    -0.09
    aldo
    -0.09
    ETA
    -0.09
    rian
    -0.09
    esco
    -0.09
    asso
    -0.09
    aq
    -0.09
    POSITIVE LOGITS
    .parseFloat
    0.21
     floating
    0.16
     Floating
    0.15
    (Float
    0.14
     floats
    0.14
     floated
    0.14
    -floating
    0.14
    Floating
    0.14
     Float
    0.14
     float
    0.14
    Activations Density 0.043%

    No Known Activations