© 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. 92251
    Prev
    Next
    INDEX
    Explanations

    states of being or activity

    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
     anch
    -0.09
     nod
    -0.09
     manifested
    -0.08
     unfortunate
    -0.08
    cio
    -0.08
     Holmes
    -0.08
    ucher
    -0.08
     conceal
    -0.08
    shade
    -0.08
    .Builder
    -0.08
    POSITIVE LOGITS
     flooded
    0.22
     buzzing
    0.18
     overrun
    0.17
     abl
    0.16
     dominated
    0.15
     filled
    0.15
     populated
    0.15
     reopened
    0.14
     invaded
    0.14
     usefulness
    0.14
    Activations Density 0.176%

    No Known Activations