© 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. 26057
    Prev
    Next
    INDEX
    Explanations

    questions starting with when

    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
    ilik
    -0.10
     eventual
    -0.09
    warz
    -0.08
     anytime
    -0.08
     subsequent
    -0.08
     adul
    -0.08
     awakened
    -0.08
     lash
    -0.08
     Marble
    -0.08
     Shades
    -0.08
    POSITIVE LOGITS
    esh
    0.12
     begins
    0.11
     Matte
    0.11
    rex
    0.11
    ISH
    0.10
    jour
    0.10
     onwards
    0.10
     wrinkles
    0.10
    /start
    0.10
     boys
    0.10
    Activations Density 0.044%

    No Known Activations