© 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. 46607
    Prev
    Next
    INDEX
    Explanations

    seeing and anticipation

    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
    lies
    -0.08
     unb
    -0.08
     Kolkata
    -0.08
    usercontent
    -0.08
     Glenn
    -0.08
     âĦĸ
    -0.08
    leigh
    -0.07
     biology
    -0.07
    ibia
    -0.07
    urga
    -0.07
    POSITIVE LOGITS
     see
    0.12
     soon
    0.11
     later
    0.11
    RIX
    0.11
    see
    0.11
     See
    0.10
    BOR
    0.10
    eph
    0.10
    antes
    0.10
     indeed
    0.09
    Activations Density 0.032%

    No Known Activations