© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48996
    Prev
    Next
    INDEX
    Explanations

    changing the topic or focus

    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
     stub
    -0.09
    cken
    -0.09
     uncertain
    -0.09
    ikan
    -0.09
    ih
    -0.09
    ikh
    -0.08
    licht
    -0.08
     Electron
    -0.08
     Twitch
    -0.08
     twitch
    -0.08
    POSITIVE LOGITS
     unrelated
    0.23
     distraction
    0.20
     distract
    0.20
     diversion
    0.20
     divert
    0.20
     topic
    0.19
     focus
    0.19
     distracting
    0.18
     diverted
    0.17
     focusing
    0.17
    Activations Density 0.019%

    No Known Activations