© 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. 25678
    Prev
    Next
    INDEX
    Explanations

    emerge or break out

    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
     Corner
    -0.11
     corner
    -0.09
     reversible
    -0.09
     reservation
    -0.09
     Reservation
    -0.09
    OG
    -0.09
     incur
    -0.09
    Closing
    -0.09
     Closing
    -0.08
    737
    -0.08
    POSITIVE LOGITS
     emergence
    0.41
     emerge
    0.39
     emerging
    0.39
     emerges
    0.37
     emerged
    0.37
     Emerging
    0.34
     Emer
    0.31
    Emer
    0.30
     emerg
    0.29
     birth
    0.24
    Activations Density 0.316%

    No Known Activations