© 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. 114435
    Prev
    Next
    INDEX
    Explanations

    look followed by up, at, or away

    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
     silently
    -0.10
     quietly
    -0.10
    uw
    -0.09
     crumbs
    -0.09
     Vib
    -0.08
     endlessly
    -0.08
    ĥģ
    -0.08
     formally
    -0.08
     TER
    -0.08
     worsh
    -0.08
    POSITIVE LOGITS
     away
    0.10
     direct
    0.10
     lest
    0.10
    IDs
    0.10
     anywhere
    0.10
     directly
    0.09
    ede
    0.09
     genital
    0.09
     Prague
    0.09
     Spe
    0.09
    Activations Density 0.019%

    No Known Activations