© 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. 49183
    Prev
    Next
    INDEX
    Explanations

    burst into, out, from, of

    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
     circulating
    -0.09
    omb
    -0.09
    yar
    -0.08
    arna
    -0.08
    itten
    -0.08
    ி
    -0.08
     Paras
    -0.08
     ramps
    -0.08
    hz
    -0.08
    oub
    -0.08
    POSITIVE LOGITS
     flames
    0.15
     Flames
    0.14
     forth
    0.14
     flame
    0.12
     conce
    0.12
    /flutter
    0.11
     burst
    0.11
     Burst
    0.11
    ed
    0.11
     laughing
    0.11
    Activations Density 0.008%

    No Known Activations