© 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. 33760
    Prev
    Next
    INDEX
    Explanations

    king or king's following word

    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
    à¹ī
    -0.11
     intrig
    -0.10
     lingering
    -0.10
    ideos
    -0.09
     irre
    -0.09
     grinding
    -0.09
     irreversible
    -0.08
     ex
    -0.08
     exemptions
    -0.08
    antro
    -0.08
    POSITIVE LOGITS
    룬
    0.08
    /pr
    0.08
    .JOptionPane
    0.08
     Cage
    0.08
    _secs
    0.08
     amateur
    0.08
    observe
    0.07
    CPP
    0.07
     sizing
    0.07
     IO
    0.07
    Activations Density 0.083%

    No Known Activations