© 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. 115707
    Prev
    Next
    INDEX
    Explanations

    numbers and places

    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
     nowadays
    -0.24
     tonight
    -0.21
     today
    -0.21
     lately
    -0.20
     presently
    -0.17
     meanwhile
    -0.16
     afterward
    -0.16
     recently
    -0.16
     someday
    -0.16
     now
    -0.16
    POSITIVE LOGITS
    ante
    0.09
    chin
    0.08
     again
    0.08
     CEL
    0.08
     Ket
    0.07
    ost
    0.07
     BB
    0.07
     tally
    0.07
     Hick
    0.07
     inst
    0.07
    Activations Density 1.281%

    No Known Activations