© 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. 25820
    Prev
    Next
    INDEX
    Explanations

    Zen or Zeno prefixes (Zenoss, Zenit, Zenith, Zeno)

    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
     incor
    -0.10
    olk
    -0.10
    abic
    -0.10
     sparing
    -0.10
    isations
    -0.10
    izations
    -0.09
    ие
    -0.09
    INGS
    -0.09
     Tel
    -0.09
    vu
    -0.09
    POSITIVE LOGITS
    ith
    0.14
    _QUOTES
    0.09
    Mate
    0.09
     master
    0.09
    endor
    0.09
    cond
    0.09
    obia
    0.09
    lope
    0.09
    ITH
    0.09
    eca
    0.08
    Activations Density 0.028%

    No Known Activations