© 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. 28159
    Prev
    Next
    INDEX
    Explanations

    common occurrence nowadays

    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
    sta
    -0.11
     Invent
    -0.11
     lick
    -0.11
    -overlay
    -0.10
    ewan
    -0.10
     overlays
    -0.10
    osos
    -0.10
    ictim
    -0.10
    vey
    -0.10
     consistently
    -0.09
    POSITIVE LOGITS
     nowadays
    0.16
     occurrence
    0.13
     especially
    0.12
     lately
    0.12
     among
    0.11
     Especially
    0.10
    especially
    0.10
     amongst
    0.10
    638
    0.10
     Nowadays
    0.10
    Activations Density 0.597%

    No Known Activations