© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 14165
    Prev
    Next
    INDEX
    Explanations

    bursting, burst, exploded, collapsed

    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
    685
    -0.09
    .sd
    -0.09
    iffin
    -0.09
     hesitate
    -0.09
     ponder
    -0.09
     linger
    -0.08
    _pd
    -0.08
     Volt
    -0.08
    toolbox
    -0.08
     hes
    -0.08
    POSITIVE LOGITS
     erupt
    0.13
     confess
    0.11
     exploded
    0.11
     collapsed
    0.11
    ork
    0.11
     admitting
    0.11
     succ
    0.11
     Burst
    0.10
    adia
    0.10
     burst
    0.10
    Activations Density 0.018%

    No Known Activations