© 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. 47747
    Prev
    Next
    INDEX
    Explanations

    birth, passage, emerging

    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
     inset
    -0.13
     Nich
    -0.11
    ixer
    -0.11
     Curtain
    -0.11
     Inputs
    -0.11
     DAR
    -0.11
    afen
    -0.11
     scatter
    -0.11
    indo
    -0.11
     wa
    -0.11
    POSITIVE LOGITS
     exit
    0.16
     exiting
    0.15
     emerging
    0.15
     emerge
    0.14
     passage
    0.13
     passed
    0.13
     Exit
    0.13
     emergence
    0.13
     emerges
    0.13
     passing
    0.13
    Activations Density 0.074%

    No Known Activations