© 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. 33086
    Prev
    Next
    INDEX
    Explanations

    how, feeling, or question intensifiers

    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
    croft
    -0.12
     a
    -0.12
    ewe
    -0.11
    397
    -0.11
    etto
    -0.10
     an
    -0.10
    ertime
    -0.10
     prem
    -0.10
    IMS
    -0.10
    ble
    -0.10
    POSITIVE LOGITS
     how
    0.15
    how
    0.10
     hoe
    0.09
     HOW
    0.08
     feeling
    0.08
     cómo
    0.07
     Feeling
    0.07
     level
    0.06
     Ago
    0.06
    -how
    0.06
    Activations Density 0.184%

    No Known Activations