© 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. 116269
    Prev
    Next
    INDEX
    Explanations

    Since followed by temporal or descriptive phrases

    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
    uct
    -0.09
    -goal
    -0.09
    869
    -0.09
     curled
    -0.08
    uell
    -0.08
    iona
    -0.08
     creed
    -0.08
    471
    -0.08
    ftime
    -0.08
    usual
    -0.08
    POSITIVE LOGITS
     then
    0.13
     decades
    0.11
     centuries
    0.10
     childhood
    0.10
     Stanton
    0.10
     acc
    0.09
    mina
    0.09
     graduating
    0.09
     Appe
    0.09
     Governments
    0.09
    Activations Density 0.031%

    No Known Activations