© 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. 4643
    Prev
    Next
    INDEX
    Explanations

    be aware/flexible/polite

    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
     guid
    -0.09
     TICK
    -0.09
     flatten
    -0.09
    -disabled
    -0.09
     privat
    -0.09
    /o
    -0.08
    èĩ
    -0.08
    -bodied
    -0.08
     flatt
    -0.08
     tw
    -0.08
    POSITIVE LOGITS
    bast
    0.10
    orges
    0.09
     communic
    0.09
     adaptable
    0.09
     upfront
    0.09
    agg
    0.09
     Respect
    0.09
    ipur
    0.09
    conc
    0.08
     respectful
    0.08
    Activations Density 0.001%

    No Known Activations