© 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. 6664
    Prev
    Next
    INDEX
    Explanations

    numbers followed by nouns

    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
     hundreds
    -0.15
     thousands
    -0.13
     Hundreds
    -0.13
     Thousands
    -0.13
     dozens
    -0.12
     billions
    -0.11
    Thousands
    -0.11
    Hundreds
    -0.11
     countless
    -0.11
     Watt
    -0.10
    POSITIVE LOGITS
     different
    0.21
     distinct
    0.20
     separate
    0.20
     (!
    0.19
    (!
    0.18
     seperate
    0.18
    -way
    0.17
    fold
    0.17
    -plus
    0.16
    teenth
    0.16
    Activations Density 0.520%

    No Known Activations