© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48581
    Prev
    Next
    INDEX
    Explanations

    I/we followed by modal verbs or 'm

    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
     plastic
    -0.09
     Deer
    -0.09
     Chatt
    -0.08
    wy
    -0.08
    ?page
    -0.08
    abar
    -0.08
    NZ
    -0.07
     uniform
    -0.07
     Elk
    -0.07
     hors
    -0.07
    POSITIVE LOGITS
     now
    0.15
     unfortunately
    0.14
     sadly
    0.13
     thankfully
    0.13
     nonetheless
    0.12
     admittedly
    0.12
     fortunately
    0.12
     luckily
    0.12
     somehow
    0.12
     hopefully
    0.11
    Activations Density 0.072%

    No Known Activations